DRAFT investigate benchmark 21566

[kosiew]

Investigate benchmark difference between

v1 - #21566 (comment) - benchmark showed improvement
v2 - #21566 (comment) - benchmark largely unchanged

comparing v1 → v2, the big story is substantially better memory usage, while the branch’s previous runtime advantage mostly disappears.

Metric	v1 Base	v1 Branch	v2 Base	v2 Branch	v2 Branch vs Base
Wall time	90.0s	85.0s	85.0s	85.0s	0%
Peak memory	11.5 GiB	11.9 GiB	9.6 GiB	10.4 GiB	+8.3% 🔴
Avg memory	4.8 GiB	4.6 GiB	4.3 GiB	4.6 GiB	+7.0% 🔴
CPU user	902.2s	853.8s	848.2s	846.0s	-0.3%
CPU sys	63.3s	60.2s	58.8s	58.9s	~0%
Peak spill	0 B	0 B	0 B	0 B	—

The interesting v1 → v2 branch changes are: wall time stays 85s, peak memory drops 11.9 → 10.4 GiB (-12.6%), CPU user drops 853.8 → 846.0s (-0.9%), and CPU sys drops 60.2 → 58.9s (-2.2%). Average memory is unchanged at 4.6 GiB.

So overall, v2 is more resource-efficient than v1, especially on peak memory. However, relative to its own v2 base, the branch now has essentially no runtime/CPU advantage and consumes more memory (+0.8 GiB peak, +0.3 GiB average).

One caveat: the v2 base itself improved quite a lot versus v1 base, so the loss of the branch's relative advantage isn't because the branch got slower—the baseline caught up.

[kosiew]

run benchmark clickbench_pushdown

[adriangbot]

Benchmark for this request failed.

Run configuration

run benchmark clickbench_pushdown

Last 20 lines of output:

Click to expand

 * [new tag]             48.0.0-rc1           -> 48.0.0-rc1
 * [new tag]             48.0.0-rc2           -> 48.0.0-rc2
 * [new tag]             5.0.0                -> 5.0.0
 * [new tag]             5.0.0-rc1            -> 5.0.0-rc1
 * [new tag]             5.0.0-rc3            -> 5.0.0-rc3
 * [new tag]             6.0.0                -> 6.0.0
 * [new tag]             6.0.0-rc0            -> 6.0.0-rc0
 * [new tag]             7.0.0                -> 7.0.0
 * [new tag]             7.0.0-rc2            -> 7.0.0-rc2
 * [new tag]             8.0.0                -> 8.0.0
 * [new tag]             8.0.0-rc1            -> 8.0.0-rc1
 * [new tag]             8.0.0-rc2            -> 8.0.0-rc2
 * [new tag]             9.0.0                -> 9.0.0
 * [new tag]             9.0.0-rc1            -> 9.0.0-rc1
 * [new tag]             ballista-0.5.0       -> ballista-0.5.0
 * [new tag]             ballista-0.6.0       -> ballista-0.6.0
 * [new tag]             ballista-0.7.0       -> ballista-0.7.0
 * [new tag]             python-0.3.0         -> python-0.3.0
 * [new tag]             python-0.4.0         -> python-0.4.0
Switched to branch 'benchmark-21566'

---

File an issue against this benchmark runner

[kosiew]

run benchmark clickbench_pushdown

[adriangbot]

Benchmark for this request failed.

Run configuration

run benchmark clickbench_pushdown

Last 20 lines of output:

Click to expand

 * [new tag]             48.0.0-rc1           -> 48.0.0-rc1
 * [new tag]             48.0.0-rc2           -> 48.0.0-rc2
 * [new tag]             5.0.0                -> 5.0.0
 * [new tag]             5.0.0-rc1            -> 5.0.0-rc1
 * [new tag]             5.0.0-rc3            -> 5.0.0-rc3
 * [new tag]             6.0.0                -> 6.0.0
 * [new tag]             6.0.0-rc0            -> 6.0.0-rc0
 * [new tag]             7.0.0                -> 7.0.0
 * [new tag]             7.0.0-rc2            -> 7.0.0-rc2
 * [new tag]             8.0.0                -> 8.0.0
 * [new tag]             8.0.0-rc1            -> 8.0.0-rc1
 * [new tag]             8.0.0-rc2            -> 8.0.0-rc2
 * [new tag]             9.0.0                -> 9.0.0
 * [new tag]             9.0.0-rc1            -> 9.0.0-rc1
 * [new tag]             ballista-0.5.0       -> ballista-0.5.0
 * [new tag]             ballista-0.6.0       -> ballista-0.6.0
 * [new tag]             ballista-0.7.0       -> ballista-0.7.0
 * [new tag]             python-0.3.0         -> python-0.3.0
 * [new tag]             python-0.4.0         -> python-0.4.0
Switched to branch 'benchmark-21566'

---

File an issue against this benchmark runner

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (main@95398f0). Learn more about missing BASE report.

Additional details and impacted files

@@           Coverage Diff           @@
##             main   #24214   +/-   ##
=======================================
  Coverage        ?   81.05%           
=======================================
  Files           ?     1106           
  Lines           ?   382268           
  Branches        ?   382268           
=======================================
  Hits            ?   309857           
  Misses          ?    54114           
  Partials        ?    18297           

☔ 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.

[kumarUjjawal]

Hi @kosiew I think you will merge main to the pr branch and then rerun the bench.

[kosiew]

@kumarUjjawal
Thanks for the suggestion.

I am trying to compare:
v1 Base (main earlier commit)
vs
v2 Base (main later commit).

Context:
v1 branch (earlier) - changes showed benchmark improvement
v2 Branch - changes did not show expected improvement

My hypothesis - the benchmark difference is due to main changes, observed from the v1, v2 Base memory and timings.

[kosiew]

run benchmark clickbench_pushdown clickbench_partitioned

[adriangbot]

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c5264626678-1564-hnfnk 6.12.85+ #1 SMP Wed Jun 17 20:31:55 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 benchmark-21566 (9ecb48a) to c08832d (merge-base) diff

Run configuration

run benchmark clickbench_pushdown

Results will be posted here when complete

---

File an issue against this benchmark runner

[adriangbot]

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c5264626678-1565-ccjmb 6.12.85+ #1 SMP Wed Jun 17 20:31:55 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 benchmark-21566 (9ecb48a) to c08832d (merge-base) diff

Run configuration

run benchmark clickbench_partitioned

Results will be posted here when complete

---

File an issue against this benchmark runner

[adriangbot]

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

Comparing benchmark-21566 (9ecb48a) to c08832d (merge-base) diff

Run configuration

run benchmark clickbench_pushdown

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 benchmark-21566
--------------------
Benchmark clickbench_pushdown.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┓
┃ Query     ┃       HEAD ┃ benchmark-21566 ┃       Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━┩
│ QQuery 0  │    1.29 ms │         1.22 ms │    no change │
│ QQuery 1  │   12.68 ms │        12.98 ms │    no change │
│ QQuery 2  │   37.52 ms │        37.01 ms │    no change │
│ QQuery 3  │   31.06 ms │        30.94 ms │    no change │
│ QQuery 4  │  228.27 ms │       226.36 ms │    no change │
│ QQuery 5  │  277.37 ms │       271.61 ms │    no change │
│ QQuery 6  │    1.31 ms │         1.25 ms │    no change │
│ QQuery 7  │   16.55 ms │        16.47 ms │    no change │
│ QQuery 8  │  332.55 ms │       324.07 ms │    no change │
│ QQuery 9  │  454.05 ms │       447.49 ms │    no change │
│ QQuery 10 │   94.18 ms │        93.71 ms │    no change │
│ QQuery 11 │  104.33 ms │       105.44 ms │    no change │
│ QQuery 12 │  298.58 ms │       298.89 ms │    no change │
│ QQuery 13 │  402.81 ms │       414.27 ms │    no change │
│ QQuery 14 │  316.16 ms │       318.66 ms │    no change │
│ QQuery 15 │  273.18 ms │       270.65 ms │    no change │
│ QQuery 16 │  612.83 ms │       613.45 ms │    no change │
│ QQuery 17 │  621.65 ms │       630.95 ms │    no change │
│ QQuery 18 │ 1250.10 ms │      1257.98 ms │    no change │
│ QQuery 19 │   28.78 ms │        29.67 ms │    no change │
│ QQuery 20 │  517.61 ms │       517.40 ms │    no change │
│ QQuery 21 │  560.39 ms │       567.80 ms │    no change │
│ QQuery 22 │  911.90 ms │       919.20 ms │    no change │
│ QQuery 23 │  114.35 ms │       110.70 ms │    no change │
│ QQuery 24 │   37.27 ms │        37.71 ms │    no change │
│ QQuery 25 │  139.40 ms │       146.40 ms │ 1.05x slower │
│ QQuery 26 │   48.72 ms │        50.26 ms │    no change │
│ QQuery 27 │  562.39 ms │       558.21 ms │    no change │
│ QQuery 28 │ 2931.93 ms │      2931.35 ms │    no change │
│ QQuery 29 │   42.30 ms │        41.29 ms │    no change │
│ QQuery 30 │  311.50 ms │       312.05 ms │    no change │
│ QQuery 31 │  287.49 ms │       287.35 ms │    no change │
│ QQuery 32 │  933.88 ms │       969.22 ms │    no change │
│ QQuery 33 │ 1471.58 ms │      1460.54 ms │    no change │
│ QQuery 34 │ 1466.59 ms │      1468.24 ms │    no change │
│ QQuery 35 │  279.60 ms │       287.87 ms │    no change │
│ QQuery 36 │   66.35 ms │        67.38 ms │    no change │
│ QQuery 37 │   36.45 ms │        36.46 ms │    no change │
│ QQuery 38 │   34.54 ms │        39.25 ms │ 1.14x slower │
│ QQuery 39 │  129.93 ms │       134.85 ms │    no change │
│ QQuery 40 │   18.05 ms │        18.24 ms │    no change │
│ QQuery 41 │   16.75 ms │        17.26 ms │    no change │
│ QQuery 42 │   14.54 ms │        14.64 ms │    no change │
└───────────┴────────────┴─────────────────┴──────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary              ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)              │ 16328.79ms │
│ Total Time (benchmark-21566)   │ 16396.73ms │
│ Average Time (HEAD)            │   379.74ms │
│ Average Time (benchmark-21566) │   381.32ms │
│ Queries Faster                 │          0 │
│ Queries Slower                 │          2 │
│ Queries with No Change         │         41 │
│ Queries with Failure           │          0 │
└────────────────────────────────┴────────────┘

Distribution per query (min / mean ±stddev / max):

Comparing HEAD and benchmark-21566
--------------------
Benchmark clickbench_pushdown.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃                       benchmark-21566 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.29 / 4.00 ±5.33 / 14.66 ms │          1.22 / 3.95 ±5.35 / 14.65 ms │     no change │
│ QQuery 1  │        12.68 / 12.90 ±0.25 / 13.35 ms │        12.98 / 13.21 ±0.18 / 13.48 ms │     no change │
│ QQuery 2  │        37.52 / 37.93 ±0.27 / 38.25 ms │        37.01 / 37.24 ±0.19 / 37.48 ms │     no change │
│ QQuery 3  │        31.06 / 31.51 ±0.58 / 32.66 ms │        30.94 / 31.54 ±0.50 / 32.47 ms │     no change │
│ QQuery 4  │     228.27 / 233.32 ±4.37 / 241.06 ms │     226.36 / 229.61 ±2.66 / 233.74 ms │     no change │
│ QQuery 5  │     277.37 / 281.02 ±2.53 / 284.15 ms │     271.61 / 274.88 ±4.11 / 282.95 ms │     no change │
│ QQuery 6  │           1.31 / 1.46 ±0.23 / 1.92 ms │           1.25 / 1.40 ±0.21 / 1.81 ms │     no change │
│ QQuery 7  │        16.55 / 16.65 ±0.07 / 16.74 ms │        16.47 / 16.59 ±0.10 / 16.70 ms │     no change │
│ QQuery 8  │     332.55 / 335.95 ±1.95 / 338.31 ms │     324.07 / 328.82 ±3.29 / 332.86 ms │     no change │
│ QQuery 9  │    454.05 / 469.55 ±14.70 / 497.54 ms │    447.49 / 465.78 ±12.70 / 486.12 ms │     no change │
│ QQuery 10 │        94.18 / 95.21 ±1.00 / 96.47 ms │       93.71 / 97.07 ±3.95 / 104.79 ms │     no change │
│ QQuery 11 │     104.33 / 105.31 ±0.58 / 106.10 ms │     105.44 / 106.63 ±1.07 / 108.38 ms │     no change │
│ QQuery 12 │     298.58 / 303.06 ±3.86 / 307.59 ms │     298.89 / 306.84 ±5.73 / 315.79 ms │     no change │
│ QQuery 13 │    402.81 / 421.12 ±16.92 / 444.54 ms │     414.27 / 422.83 ±8.83 / 437.43 ms │     no change │
│ QQuery 14 │     316.16 / 318.16 ±1.52 / 319.89 ms │     318.66 / 324.39 ±7.50 / 338.89 ms │     no change │
│ QQuery 15 │     273.18 / 279.61 ±6.92 / 292.95 ms │    270.65 / 289.63 ±10.01 / 299.23 ms │     no change │
│ QQuery 16 │     612.83 / 618.33 ±3.96 / 623.55 ms │     613.45 / 620.75 ±5.85 / 630.88 ms │     no change │
│ QQuery 17 │    621.65 / 634.53 ±11.19 / 654.95 ms │     630.95 / 639.17 ±6.81 / 651.40 ms │     no change │
│ QQuery 18 │ 1250.10 / 1276.03 ±17.95 / 1299.82 ms │ 1257.98 / 1280.99 ±20.08 / 1304.32 ms │     no change │
│ QQuery 19 │       28.78 / 41.56 ±14.79 / 61.26 ms │        29.67 / 34.83 ±9.77 / 54.36 ms │ +1.19x faster │
│ QQuery 20 │     517.61 / 528.72 ±5.62 / 532.79 ms │     517.40 / 524.34 ±6.49 / 534.30 ms │     no change │
│ QQuery 21 │     560.39 / 569.70 ±9.16 / 582.66 ms │     567.80 / 579.66 ±9.88 / 595.79 ms │     no change │
│ QQuery 22 │     911.90 / 917.64 ±4.18 / 923.12 ms │     919.20 / 929.73 ±7.19 / 939.83 ms │     no change │
│ QQuery 23 │     114.35 / 123.43 ±9.59 / 141.48 ms │    110.70 / 121.10 ±10.29 / 139.30 ms │     no change │
│ QQuery 24 │        37.27 / 37.60 ±0.25 / 37.92 ms │        37.71 / 39.20 ±1.54 / 42.12 ms │     no change │
│ QQuery 25 │     139.40 / 148.62 ±8.64 / 160.99 ms │     146.40 / 151.13 ±3.96 / 156.97 ms │     no change │
│ QQuery 26 │        48.72 / 52.11 ±5.29 / 62.63 ms │        50.26 / 51.55 ±1.39 / 53.94 ms │     no change │
│ QQuery 27 │    562.39 / 576.79 ±11.68 / 595.00 ms │     558.21 / 572.25 ±7.81 / 580.59 ms │     no change │
│ QQuery 28 │ 2931.93 / 2947.59 ±14.74 / 2965.06 ms │ 2931.35 / 2957.08 ±26.84 / 3008.58 ms │     no change │
│ QQuery 29 │       42.30 / 50.83 ±11.07 / 70.24 ms │       41.29 / 56.97 ±18.17 / 84.32 ms │  1.12x slower │
│ QQuery 30 │     311.50 / 318.69 ±4.03 / 322.31 ms │     312.05 / 319.18 ±6.04 / 329.24 ms │     no change │
│ QQuery 31 │    287.49 / 302.00 ±18.07 / 334.88 ms │     287.35 / 296.14 ±6.35 / 303.67 ms │     no change │
│ QQuery 32 │    933.88 / 955.34 ±16.90 / 978.54 ms │   969.22 / 988.96 ±13.78 / 1009.80 ms │     no change │
│ QQuery 33 │ 1471.58 / 1481.23 ±11.11 / 1502.76 ms │ 1460.54 / 1496.23 ±23.62 / 1532.09 ms │     no change │
│ QQuery 34 │ 1466.59 / 1488.77 ±17.34 / 1517.28 ms │ 1468.24 / 1497.19 ±16.01 / 1517.53 ms │     no change │
│ QQuery 35 │    279.60 / 313.70 ±30.35 / 366.07 ms │     287.87 / 296.84 ±4.95 / 302.60 ms │ +1.06x faster │
│ QQuery 36 │        66.35 / 70.11 ±2.55 / 74.24 ms │        67.38 / 72.88 ±4.01 / 77.98 ms │     no change │
│ QQuery 37 │        36.45 / 40.03 ±3.85 / 46.25 ms │        36.46 / 39.42 ±2.50 / 42.46 ms │     no change │
│ QQuery 38 │        34.54 / 36.77 ±1.75 / 38.73 ms │        39.25 / 47.48 ±7.62 / 60.61 ms │  1.29x slower │
│ QQuery 39 │    129.93 / 146.06 ±12.33 / 167.95 ms │     134.85 / 144.01 ±7.13 / 154.66 ms │     no change │
│ QQuery 40 │        18.05 / 18.17 ±0.10 / 18.34 ms │        18.24 / 21.02 ±3.76 / 28.36 ms │  1.16x slower │
│ QQuery 41 │        16.75 / 17.04 ±0.30 / 17.59 ms │        17.26 / 21.60 ±8.37 / 38.33 ms │  1.27x slower │
│ QQuery 42 │        14.54 / 14.62 ±0.09 / 14.78 ms │        14.64 / 16.66 ±3.88 / 24.42 ms │  1.14x slower │
└───────────┴───────────────────────────────────────┴───────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary              ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)              │ 16672.78ms │
│ Total Time (benchmark-21566)   │ 16766.76ms │
│ Average Time (HEAD)            │   387.74ms │
│ Average Time (benchmark-21566) │   389.92ms │
│ Queries Faster                 │          2 │
│ Queries Slower                 │          5 │
│ Queries with No Change         │         36 │
│ Queries with Failure           │          0 │
└────────────────────────────────┴────────────┘

Resource Usage

clickbench_pushdown — base (merge-base)

Metric	Value
Wall time	85.0s
Peak memory	10.1 GiB
Avg memory	4.7 GiB
CPU user	852.8s
CPU sys	57.1s
Peak spill	0 B

clickbench_pushdown — branch

Metric	Value
Wall time	85.0s
Peak memory	11.4 GiB
Avg memory	4.9 GiB
CPU user	854.7s
CPU sys	61.8s
Peak spill	0 B

---

File an issue against this benchmark runner

[adriangbot]

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

Comparing benchmark-21566 (9ecb48a) to c08832d (merge-base) diff

Run configuration

run benchmark clickbench_partitioned

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 benchmark-21566
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃       HEAD ┃ benchmark-21566 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │    1.28 ms │         1.24 ms │     no change │
│ QQuery 1  │   12.14 ms │        12.97 ms │  1.07x slower │
│ QQuery 2  │   36.72 ms │        37.61 ms │     no change │
│ QQuery 3  │   31.40 ms │        31.22 ms │     no change │
│ QQuery 4  │  235.86 ms │       228.77 ms │     no change │
│ QQuery 5  │  283.08 ms │       278.33 ms │     no change │
│ QQuery 6  │    1.35 ms │         1.26 ms │ +1.07x faster │
│ QQuery 7  │   13.98 ms │        14.04 ms │     no change │
│ QQuery 8  │  343.10 ms │       335.54 ms │     no change │
│ QQuery 9  │  454.14 ms │       466.60 ms │     no change │
│ QQuery 10 │   71.78 ms │        70.20 ms │     no change │
│ QQuery 11 │   83.35 ms │        81.67 ms │     no change │
│ QQuery 12 │  277.98 ms │       271.53 ms │     no change │
│ QQuery 13 │  372.38 ms │       375.68 ms │     no change │
│ QQuery 14 │  292.23 ms │       288.07 ms │     no change │
│ QQuery 15 │  282.01 ms │       279.48 ms │     no change │
│ QQuery 16 │  629.59 ms │       624.31 ms │     no change │
│ QQuery 17 │  638.49 ms │       633.23 ms │     no change │
│ QQuery 18 │ 1303.73 ms │      1285.32 ms │     no change │
│ QQuery 19 │   28.31 ms │        28.61 ms │     no change │
│ QQuery 20 │  523.33 ms │       517.58 ms │     no change │
│ QQuery 21 │  521.98 ms │       514.21 ms │     no change │
│ QQuery 22 │ 1013.06 ms │       997.79 ms │     no change │
│ QQuery 23 │ 3171.66 ms │      3116.62 ms │     no change │
│ QQuery 24 │   42.03 ms │        41.39 ms │     no change │
│ QQuery 25 │  113.35 ms │       112.53 ms │     no change │
│ QQuery 26 │   42.09 ms │        41.71 ms │     no change │
│ QQuery 27 │  519.45 ms │       518.72 ms │     no change │
│ QQuery 28 │ 2935.72 ms │      2916.77 ms │     no change │
│ QQuery 29 │   42.02 ms │        41.53 ms │     no change │
│ QQuery 30 │  317.17 ms │       305.83 ms │     no change │
│ QQuery 31 │  294.32 ms │       286.47 ms │     no change │
│ QQuery 32 │ 1008.33 ms │       966.12 ms │     no change │
│ QQuery 33 │ 1527.03 ms │      1497.01 ms │     no change │
│ QQuery 34 │ 1531.71 ms │      1534.99 ms │     no change │
│ QQuery 35 │  298.09 ms │       286.77 ms │     no change │
│ QQuery 36 │   69.14 ms │        68.13 ms │     no change │
│ QQuery 37 │   37.23 ms │        36.00 ms │     no change │
│ QQuery 38 │   41.65 ms │        42.76 ms │     no change │
│ QQuery 39 │  137.13 ms │       140.12 ms │     no change │
│ QQuery 40 │   14.95 ms │        14.61 ms │     no change │
│ QQuery 41 │   14.53 ms │        14.27 ms │     no change │
│ QQuery 42 │   14.13 ms │        13.68 ms │     no change │
└───────────┴────────────┴─────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary              ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)              │ 19622.99ms │
│ Total Time (benchmark-21566)   │ 19371.30ms │
│ Average Time (HEAD)            │   456.35ms │
│ Average Time (benchmark-21566) │   450.50ms │
│ Queries Faster                 │          1 │
│ Queries Slower                 │          1 │
│ Queries with No Change         │         41 │
│ Queries with Failure           │          0 │
└────────────────────────────────┴────────────┘

Distribution per query (min / mean ±stddev / max):

Comparing HEAD and benchmark-21566
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃                       benchmark-21566 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.28 / 4.12 ±5.53 / 15.18 ms │          1.24 / 4.08 ±5.51 / 15.10 ms │     no change │
│ QQuery 1  │        12.14 / 12.73 ±0.34 / 13.19 ms │        12.97 / 13.16 ±0.15 / 13.37 ms │     no change │
│ QQuery 2  │        36.72 / 37.27 ±0.46 / 37.84 ms │        37.61 / 37.93 ±0.27 / 38.41 ms │     no change │
│ QQuery 3  │        31.40 / 31.94 ±0.50 / 32.61 ms │        31.22 / 31.40 ±0.14 / 31.59 ms │     no change │
│ QQuery 4  │     235.86 / 242.22 ±5.53 / 251.53 ms │     228.77 / 234.88 ±3.49 / 238.49 ms │     no change │
│ QQuery 5  │     283.08 / 285.49 ±1.45 / 287.34 ms │     278.33 / 281.50 ±3.24 / 286.98 ms │     no change │
│ QQuery 6  │           1.35 / 1.50 ±0.22 / 1.92 ms │           1.26 / 1.42 ±0.24 / 1.88 ms │ +1.05x faster │
│ QQuery 7  │        13.98 / 14.16 ±0.23 / 14.61 ms │        14.04 / 14.29 ±0.18 / 14.60 ms │     no change │
│ QQuery 8  │     343.10 / 345.64 ±1.94 / 347.92 ms │     335.54 / 338.91 ±4.08 / 346.73 ms │     no change │
│ QQuery 9  │    454.14 / 479.01 ±13.11 / 489.56 ms │     466.60 / 478.50 ±7.29 / 485.42 ms │     no change │
│ QQuery 10 │        71.78 / 72.74 ±0.80 / 73.72 ms │        70.20 / 75.70 ±7.48 / 89.76 ms │     no change │
│ QQuery 11 │        83.35 / 84.20 ±0.62 / 85.06 ms │        81.67 / 83.08 ±1.78 / 86.43 ms │     no change │
│ QQuery 12 │     277.98 / 284.08 ±4.65 / 290.73 ms │     271.53 / 277.56 ±6.62 / 290.20 ms │     no change │
│ QQuery 13 │     372.38 / 382.11 ±6.44 / 391.18 ms │     375.68 / 387.07 ±6.77 / 396.12 ms │     no change │
│ QQuery 14 │     292.23 / 297.25 ±4.19 / 304.95 ms │     288.07 / 295.89 ±8.01 / 309.93 ms │     no change │
│ QQuery 15 │    282.01 / 295.98 ±23.73 / 343.31 ms │     279.48 / 284.34 ±4.92 / 293.00 ms │     no change │
│ QQuery 16 │     629.59 / 640.63 ±8.72 / 655.20 ms │    624.31 / 639.27 ±11.61 / 658.26 ms │     no change │
│ QQuery 17 │    638.49 / 657.19 ±28.04 / 712.87 ms │     633.23 / 648.12 ±9.94 / 661.84 ms │     no change │
│ QQuery 18 │ 1303.73 / 1327.70 ±17.63 / 1352.07 ms │ 1285.32 / 1317.47 ±33.24 / 1374.30 ms │     no change │
│ QQuery 19 │       28.31 / 36.51 ±16.17 / 68.84 ms │        28.61 / 29.96 ±2.32 / 34.58 ms │ +1.22x faster │
│ QQuery 20 │     523.33 / 532.76 ±8.22 / 547.58 ms │    517.58 / 529.59 ±16.65 / 562.38 ms │     no change │
│ QQuery 21 │     521.98 / 526.01 ±2.47 / 528.51 ms │     514.21 / 523.45 ±5.47 / 530.58 ms │     no change │
│ QQuery 22 │  1013.06 / 1020.64 ±8.33 / 1036.74 ms │  997.79 / 1034.97 ±19.29 / 1053.77 ms │     no change │
│ QQuery 23 │ 3171.66 / 3188.12 ±12.10 / 3202.73 ms │ 3116.62 / 3160.97 ±28.16 / 3196.63 ms │     no change │
│ QQuery 24 │        42.03 / 42.22 ±0.18 / 42.53 ms │        41.39 / 42.19 ±0.79 / 43.62 ms │     no change │
│ QQuery 25 │     113.35 / 115.19 ±1.89 / 118.78 ms │     112.53 / 120.67 ±8.22 / 131.57 ms │     no change │
│ QQuery 26 │        42.09 / 44.63 ±2.78 / 49.92 ms │        41.71 / 43.19 ±0.86 / 44.39 ms │     no change │
│ QQuery 27 │     519.45 / 530.03 ±5.97 / 535.02 ms │     518.72 / 525.62 ±7.35 / 539.81 ms │     no change │
│ QQuery 28 │ 2935.72 / 2959.07 ±25.53 / 3006.91 ms │ 2916.77 / 2934.32 ±10.58 / 2949.64 ms │     no change │
│ QQuery 29 │        42.02 / 42.23 ±0.19 / 42.53 ms │        41.53 / 43.40 ±2.77 / 48.88 ms │     no change │
│ QQuery 30 │     317.17 / 320.30 ±5.25 / 330.76 ms │    305.83 / 317.90 ±14.35 / 346.05 ms │     no change │
│ QQuery 31 │     294.32 / 301.42 ±6.21 / 310.03 ms │    286.47 / 300.23 ±11.94 / 321.77 ms │     no change │
│ QQuery 32 │ 1008.33 / 1021.93 ±10.46 / 1039.87 ms │   966.12 / 986.72 ±17.73 / 1008.61 ms │     no change │
│ QQuery 33 │  1527.03 / 1536.48 ±6.19 / 1546.40 ms │ 1497.01 / 1527.94 ±22.92 / 1559.78 ms │     no change │
│ QQuery 34 │ 1531.71 / 1578.03 ±31.81 / 1623.47 ms │ 1534.99 / 1596.93 ±59.81 / 1705.94 ms │     no change │
│ QQuery 35 │    298.09 / 311.19 ±16.94 / 343.20 ms │    286.77 / 326.57 ±59.23 / 442.88 ms │     no change │
│ QQuery 36 │        69.14 / 72.12 ±3.05 / 77.43 ms │       68.13 / 79.78 ±11.84 / 99.55 ms │  1.11x slower │
│ QQuery 37 │        37.23 / 44.45 ±4.78 / 52.13 ms │        36.00 / 36.98 ±0.86 / 38.07 ms │ +1.20x faster │
│ QQuery 38 │        41.65 / 43.78 ±1.28 / 45.15 ms │        42.76 / 44.97 ±2.48 / 49.52 ms │     no change │
│ QQuery 39 │    137.13 / 158.55 ±16.82 / 179.26 ms │     140.12 / 150.39 ±7.83 / 162.09 ms │ +1.05x faster │
│ QQuery 40 │        14.95 / 15.15 ±0.17 / 15.38 ms │        14.61 / 15.06 ±0.57 / 16.18 ms │     no change │
│ QQuery 41 │        14.53 / 14.65 ±0.08 / 14.74 ms │        14.27 / 14.43 ±0.12 / 14.64 ms │     no change │
│ QQuery 42 │        14.13 / 14.22 ±0.06 / 14.32 ms │        13.68 / 15.51 ±3.14 / 21.77 ms │  1.09x slower │
└───────────┴───────────────────────────────────────┴───────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary              ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)              │ 19965.62ms │
│ Total Time (benchmark-21566)   │ 19846.31ms │
│ Average Time (HEAD)            │   464.32ms │
│ Average Time (benchmark-21566) │   461.54ms │
│ Queries Faster                 │          4 │
│ Queries Slower                 │          2 │
│ Queries with No Change         │         37 │
│ Queries with Failure           │          0 │
└────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric	Value
Wall time	105.0s
Peak memory	12.0 GiB
Avg memory	4.7 GiB
CPU user	1023.0s
CPU sys	72.7s
Peak spill	0 B

clickbench_partitioned — branch

Metric	Value
Wall time	100.0s
Peak memory	11.3 GiB
Avg memory	4.6 GiB
CPU user	1013.1s
CPU sys	72.7s
Peak spill	0 B

---

File an issue against this benchmark runner