Introduce Morselizer API by alamb · Pull Request #21327 · apache/datafusion

alamb · 2026-04-02T19:26:01Z

(Draft until I am sure I can use this API to make FileStream behave better)

Which issue does this PR close?

part of Introduce morsel-driven Parquet scan #20529
Broken out of Sketch out a Morselize API #20820

Rationale for this change

I am reworking how the FileStream works so that it can reorder operations at runtime. Eventually that will include both CPU and IO

This PR is a step in the direction by introducing the main Morsel API and implementing it for Parquet

What changes are included in this PR?

Add proposed Morsel API
Rewrite Parquet opener in terms of that API
Add an adapter layer (back to FileOpener, so I don't have to rewrite FileStream in the same PR)

My next PR will rewrite the FileStream to use the Morsel API

Are these changes tested?

Yes by existing CI.

I will work on adding additional tests for just Parquet opener in a follow on PR

Are there any user-facing changes?

No

alamb · 2026-04-02T20:40:27Z

run benchmarks

alamb · 2026-04-02T20:40:36Z

run benchmark clickbench_partitioned

alamb · 2026-04-02T20:40:39Z

run benchmark tpch

adriangbot · 2026-04-02T20:43:07Z

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4180363567-679-znm7p 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing alamb/morsel_api_2 (9d4457c) to c8aefab (merge-base) diff using: tpcds
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-04-02T20:43:08Z

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4180363567-678-rv6j4 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing alamb/morsel_api_2 (9d4457c) to c8aefab (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-04-02T20:43:08Z

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4180364180-681-kf65h 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing alamb/morsel_api_2 (9d4457c) to c8aefab (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-04-02T20:43:09Z

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4180363567-680-s44pb 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing alamb/morsel_api_2 (9d4457c) to c8aefab (merge-base) diff using: tpch
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-04-02T20:43:12Z

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4180364390-682-n5kpm 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing alamb/morsel_api_2 (9d4457c) to c8aefab (merge-base) diff using: tpch
Results will be posted here when complete

File an issue against this benchmark runner

adriangb · 2026-04-02T20:49:40Z

It would be nice to see the path for the morsel APIs to supplant the existing ones in a backward compatible manner. In my previous attempts I made FileOpener ~ Morselizer (by adding a method along the lines of FileOpener::plan_file that defaults to packaging up the entire file as a morsel mixing IO and CPU. That means that we can migrate data sources one by one but immediately remove any legacy FileStream code and whatnot.

adriangbot · 2026-04-02T20:54:41Z

🤖 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 alamb_morsel_api_2
--------------------
Benchmark tpch_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Query     ┃                           HEAD ┃             alamb_morsel_api_2 ┃    Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ QQuery 1  │ 45.40 / 45.99 ±0.81 / 47.56 ms │ 45.52 / 46.45 ±1.08 / 48.14 ms │ no change │
│ QQuery 2  │ 20.99 / 21.33 ±0.34 / 21.95 ms │ 20.96 / 21.12 ±0.10 / 21.24 ms │ no change │
│ QQuery 3  │ 31.68 / 32.40 ±1.04 / 34.45 ms │ 31.83 / 32.26 ±0.34 / 32.85 ms │ no change │
│ QQuery 4  │ 20.49 / 21.53 ±0.75 / 22.36 ms │ 20.97 / 21.86 ±0.75 / 22.96 ms │ no change │
│ QQuery 5  │ 47.26 / 49.60 ±1.50 / 51.46 ms │ 47.82 / 50.98 ±1.63 / 52.29 ms │ no change │
│ QQuery 6  │ 17.09 / 17.84 ±0.93 / 19.66 ms │ 17.34 / 17.51 ±0.12 / 17.64 ms │ no change │
│ QQuery 7  │ 55.07 / 56.44 ±0.69 / 56.97 ms │ 54.67 / 55.49 ±0.76 / 56.75 ms │ no change │
│ QQuery 8  │ 47.64 / 48.27 ±0.47 / 48.80 ms │ 48.04 / 48.38 ±0.31 / 48.93 ms │ no change │
│ QQuery 9  │ 53.76 / 55.06 ±1.07 / 56.64 ms │ 54.46 / 55.12 ±0.52 / 55.88 ms │ no change │
│ QQuery 10 │ 71.20 / 73.05 ±1.46 / 75.23 ms │ 70.82 / 71.74 ±1.08 / 73.81 ms │ no change │
│ QQuery 11 │ 13.70 / 14.25 ±0.47 / 14.98 ms │ 13.79 / 14.56 ±1.13 / 16.80 ms │ no change │
│ QQuery 12 │ 27.97 / 28.38 ±0.41 / 29.17 ms │ 28.33 / 28.52 ±0.16 / 28.76 ms │ no change │
│ QQuery 13 │ 38.57 / 39.76 ±0.90 / 40.66 ms │ 37.87 / 39.16 ±0.77 / 40.03 ms │ no change │
│ QQuery 14 │ 28.51 / 28.90 ±0.44 / 29.76 ms │ 28.77 / 29.23 ±0.28 / 29.54 ms │ no change │
│ QQuery 15 │ 33.42 / 33.65 ±0.21 / 34.04 ms │ 33.83 / 34.41 ±0.46 / 35.15 ms │ no change │
│ QQuery 16 │ 16.27 / 16.50 ±0.18 / 16.71 ms │ 15.80 / 16.63 ±0.68 / 17.85 ms │ no change │
│ QQuery 17 │ 72.73 / 73.20 ±0.56 / 74.25 ms │ 72.38 / 73.52 ±1.18 / 75.70 ms │ no change │
│ QQuery 18 │ 77.21 / 79.23 ±1.13 / 80.57 ms │ 76.87 / 78.68 ±1.20 / 80.30 ms │ no change │
│ QQuery 19 │ 37.62 / 38.27 ±0.71 / 39.63 ms │ 37.69 / 37.95 ±0.25 / 38.41 ms │ no change │
│ QQuery 20 │ 40.33 / 41.70 ±0.87 / 42.70 ms │ 40.13 / 41.34 ±0.65 / 42.01 ms │ no change │
│ QQuery 21 │ 65.18 / 66.50 ±1.12 / 67.97 ms │ 64.75 / 67.06 ±1.89 / 69.14 ms │ no change │
│ QQuery 22 │ 17.52 / 17.89 ±0.26 / 18.28 ms │ 17.92 / 18.43 ±0.49 / 19.26 ms │ no change │
└───────────┴────────────────────────────────┴────────────────────────────────┴───────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┓
┃ Benchmark Summary                 ┃          ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━┩
│ Total Time (HEAD)                 │ 899.74ms │
│ Total Time (alamb_morsel_api_2)   │ 900.39ms │
│ Average Time (HEAD)               │  40.90ms │
│ Average Time (alamb_morsel_api_2) │  40.93ms │
│ Queries Faster                    │        0 │
│ Queries Slower                    │        0 │
│ Queries with No Change            │       22 │
│ Queries with Failure              │        0 │
└───────────────────────────────────┴──────────┘

Resource Usage

tpch — base (merge-base)

Metric	Value
Wall time	4.8s
Peak memory	4.0 GiB
Avg memory	3.6 GiB
CPU user	33.4s
CPU sys	2.9s
Disk read	0 B
Disk write	136.0 KiB

tpch — branch

Metric	Value
Wall time	4.7s
Peak memory	4.0 GiB
Avg memory	3.6 GiB
CPU user	33.7s
CPU sys	2.8s
Disk read	0 B
Disk write	60.0 KiB

File an issue against this benchmark runner

adriangbot · 2026-04-02T20:54:42Z

🤖 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 alamb_morsel_api_2
--------------------
Benchmark tpch_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Query     ┃                           HEAD ┃             alamb_morsel_api_2 ┃    Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ QQuery 1  │ 45.81 / 46.83 ±1.04 / 48.50 ms │ 45.54 / 46.22 ±0.69 / 47.46 ms │ no change │
│ QQuery 2  │ 21.33 / 21.52 ±0.16 / 21.72 ms │ 21.11 / 21.43 ±0.25 / 21.86 ms │ no change │
│ QQuery 3  │ 31.78 / 32.06 ±0.29 / 32.56 ms │ 31.70 / 31.95 ±0.25 / 32.33 ms │ no change │
│ QQuery 4  │ 20.84 / 21.70 ±0.55 / 22.53 ms │ 20.82 / 21.96 ±0.62 / 22.63 ms │ no change │
│ QQuery 5  │ 48.02 / 51.28 ±1.73 / 53.16 ms │ 47.68 / 49.28 ±1.52 / 51.43 ms │ no change │
│ QQuery 6  │ 17.15 / 17.64 ±0.43 / 18.44 ms │ 17.20 / 17.31 ±0.12 / 17.52 ms │ no change │
│ QQuery 7  │ 54.27 / 56.31 ±1.34 / 58.48 ms │ 53.55 / 55.33 ±1.08 / 56.44 ms │ no change │
│ QQuery 8  │ 47.86 / 48.42 ±0.48 / 49.16 ms │ 48.18 / 48.61 ±0.38 / 49.11 ms │ no change │
│ QQuery 9  │ 53.84 / 54.79 ±0.51 / 55.24 ms │ 54.59 / 56.18 ±1.45 / 58.56 ms │ no change │
│ QQuery 10 │ 71.12 / 71.82 ±0.79 / 73.26 ms │ 72.08 / 73.10 ±1.34 / 75.68 ms │ no change │
│ QQuery 11 │ 13.97 / 14.36 ±0.47 / 15.24 ms │ 13.96 / 14.67 ±0.78 / 16.13 ms │ no change │
│ QQuery 12 │ 27.81 / 28.06 ±0.22 / 28.46 ms │ 27.77 / 28.19 ±0.39 / 28.77 ms │ no change │
│ QQuery 13 │ 38.45 / 39.12 ±0.42 / 39.58 ms │ 39.64 / 40.14 ±0.45 / 40.75 ms │ no change │
│ QQuery 14 │ 28.47 / 29.26 ±0.86 / 30.65 ms │ 28.32 / 28.72 ±0.40 / 29.46 ms │ no change │
│ QQuery 15 │ 33.26 / 33.87 ±0.43 / 34.36 ms │ 33.82 / 34.12 ±0.36 / 34.81 ms │ no change │
│ QQuery 16 │ 16.01 / 16.23 ±0.22 / 16.64 ms │ 16.06 / 16.40 ±0.21 / 16.64 ms │ no change │
│ QQuery 17 │ 72.71 / 73.71 ±0.55 / 74.40 ms │ 74.45 / 75.72 ±1.37 / 77.86 ms │ no change │
│ QQuery 18 │ 78.10 / 78.74 ±1.03 / 80.77 ms │ 77.70 / 78.49 ±0.50 / 79.23 ms │ no change │
│ QQuery 19 │ 37.48 / 37.81 ±0.33 / 38.33 ms │ 37.03 / 37.57 ±0.47 / 38.35 ms │ no change │
│ QQuery 20 │ 40.22 / 41.04 ±0.67 / 41.94 ms │ 40.87 / 41.50 ±0.44 / 41.97 ms │ no change │
│ QQuery 21 │ 63.44 / 65.69 ±1.72 / 67.75 ms │ 64.00 / 65.57 ±0.90 / 66.61 ms │ no change │
│ QQuery 22 │ 17.72 / 18.09 ±0.21 / 18.31 ms │ 17.74 / 18.10 ±0.33 / 18.72 ms │ no change │
└───────────┴────────────────────────────────┴────────────────────────────────┴───────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┓
┃ Benchmark Summary                 ┃          ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━┩
│ Total Time (HEAD)                 │ 898.36ms │
│ Total Time (alamb_morsel_api_2)   │ 900.56ms │
│ Average Time (HEAD)               │  40.83ms │
│ Average Time (alamb_morsel_api_2) │  40.93ms │
│ Queries Faster                    │        0 │
│ Queries Slower                    │        0 │
│ Queries with No Change            │       22 │
│ Queries with Failure              │        0 │
└───────────────────────────────────┴──────────┘

Resource Usage

tpch — base (merge-base)

Metric	Value
Wall time	4.8s
Peak memory	4.1 GiB
Avg memory	3.6 GiB
CPU user	33.5s
CPU sys	2.9s
Disk read	0 B
Disk write	136.0 KiB

tpch — branch

Metric	Value
Wall time	4.7s
Peak memory	4.1 GiB
Avg memory	3.6 GiB
CPU user	33.5s
CPU sys	2.9s
Disk read	0 B
Disk write	60.0 KiB

File an issue against this benchmark runner

adriangbot · 2026-04-02T21:00:11Z

🤖 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 alamb_morsel_api_2
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃                    alamb_morsel_api_2 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.28 / 4.46 ±6.29 / 17.05 ms │          1.28 / 4.45 ±6.27 / 16.99 ms │     no change │
│ QQuery 1  │        14.11 / 14.56 ±0.29 / 14.90 ms │        14.10 / 14.57 ±0.33 / 15.01 ms │     no change │
│ QQuery 2  │        44.41 / 44.70 ±0.40 / 45.48 ms │        44.83 / 45.24 ±0.23 / 45.47 ms │     no change │
│ QQuery 3  │        42.97 / 44.61 ±1.25 / 45.84 ms │        43.04 / 44.58 ±1.06 / 46.26 ms │     no change │
│ QQuery 4  │    281.45 / 299.87 ±12.54 / 319.73 ms │     287.14 / 298.60 ±7.70 / 310.66 ms │     no change │
│ QQuery 5  │     342.84 / 347.54 ±4.00 / 353.23 ms │     342.02 / 347.62 ±4.38 / 352.97 ms │     no change │
│ QQuery 6  │           5.31 / 6.08 ±0.52 / 6.60 ms │           5.08 / 5.52 ±0.47 / 6.36 ms │ +1.10x faster │
│ QQuery 7  │        16.42 / 17.02 ±0.61 / 18.09 ms │        16.58 / 16.71 ±0.12 / 16.93 ms │     no change │
│ QQuery 8  │    427.77 / 438.75 ±13.47 / 464.52 ms │     429.20 / 437.01 ±4.45 / 442.62 ms │     no change │
│ QQuery 9  │     626.30 / 634.17 ±6.38 / 645.32 ms │     628.37 / 630.63 ±2.57 / 635.36 ms │     no change │
│ QQuery 10 │        90.90 / 93.56 ±1.43 / 95.16 ms │        91.13 / 93.95 ±2.47 / 98.15 ms │     no change │
│ QQuery 11 │     103.45 / 104.84 ±1.39 / 106.71 ms │     104.17 / 106.79 ±1.60 / 108.23 ms │     no change │
│ QQuery 12 │     342.30 / 346.96 ±3.81 / 353.39 ms │     342.35 / 349.72 ±8.48 / 365.84 ms │     no change │
│ QQuery 13 │    446.28 / 470.84 ±17.08 / 493.30 ms │    451.38 / 472.54 ±14.43 / 493.43 ms │     no change │
│ QQuery 14 │     341.68 / 346.35 ±3.33 / 351.80 ms │     346.13 / 355.76 ±6.96 / 363.98 ms │     no change │
│ QQuery 15 │    365.12 / 372.76 ±10.95 / 394.07 ms │    374.90 / 419.56 ±34.31 / 470.40 ms │  1.13x slower │
│ QQuery 16 │    706.34 / 728.09 ±16.53 / 756.75 ms │     736.04 / 746.60 ±7.28 / 755.22 ms │     no change │
│ QQuery 17 │     715.13 / 719.26 ±4.32 / 727.27 ms │    711.37 / 728.88 ±12.78 / 744.66 ms │     no change │
│ QQuery 18 │ 1416.14 / 1452.31 ±18.55 / 1469.12 ms │ 1393.66 / 1478.36 ±50.70 / 1549.85 ms │     no change │
│ QQuery 19 │      35.95 / 60.54 ±40.12 / 140.42 ms │       35.42 / 44.29 ±15.10 / 74.34 ms │ +1.37x faster │
│ QQuery 20 │    703.46 / 725.52 ±22.70 / 763.78 ms │    713.68 / 730.04 ±19.35 / 760.66 ms │     no change │
│ QQuery 21 │     751.08 / 754.37 ±2.85 / 758.69 ms │    755.07 / 766.82 ±14.27 / 792.84 ms │     no change │
│ QQuery 22 │  1107.64 / 1115.33 ±5.42 / 1124.27 ms │  1113.66 / 1118.24 ±2.66 / 1121.44 ms │     no change │
│ QQuery 23 │ 3002.00 / 3023.78 ±13.04 / 3037.66 ms │ 3039.71 / 3078.73 ±24.69 / 3112.47 ms │     no change │
│ QQuery 24 │      94.53 / 100.93 ±3.44 / 104.53 ms │     100.72 / 103.64 ±2.19 / 107.33 ms │     no change │
│ QQuery 25 │     136.93 / 139.10 ±2.36 / 143.70 ms │     139.09 / 142.54 ±2.48 / 145.38 ms │     no change │
│ QQuery 26 │       96.78 / 98.44 ±1.59 / 101.06 ms │      97.66 / 101.16 ±2.41 / 104.19 ms │     no change │
│ QQuery 27 │    832.37 / 848.85 ±14.32 / 868.00 ms │    842.72 / 850.73 ±11.48 / 873.01 ms │     no change │
│ QQuery 28 │ 7738.92 / 7805.56 ±33.48 / 7828.23 ms │ 7715.38 / 7743.97 ±20.83 / 7779.02 ms │     no change │
│ QQuery 29 │        49.51 / 53.19 ±2.47 / 55.47 ms │        50.54 / 53.91 ±3.23 / 59.29 ms │     no change │
│ QQuery 30 │     358.36 / 364.38 ±5.07 / 371.12 ms │     364.65 / 367.27 ±2.02 / 370.81 ms │     no change │
│ QQuery 31 │    347.35 / 376.37 ±16.63 / 397.59 ms │    363.60 / 378.34 ±14.82 / 405.95 ms │     no change │
│ QQuery 32 │ 1093.95 / 1228.55 ±83.56 / 1356.11 ms │ 1034.80 / 1082.66 ±73.73 / 1227.50 ms │ +1.13x faster │
│ QQuery 33 │ 1541.48 / 1554.63 ±18.94 / 1592.16 ms │ 1444.29 / 1457.45 ±12.15 / 1476.53 ms │ +1.07x faster │
│ QQuery 34 │ 1454.98 / 1509.19 ±57.11 / 1605.51 ms │ 1442.79 / 1461.89 ±10.90 / 1473.50 ms │     no change │
│ QQuery 35 │     380.54 / 386.13 ±4.00 / 391.33 ms │     388.73 / 390.37 ±1.75 / 392.56 ms │     no change │
│ QQuery 36 │     112.48 / 119.40 ±5.19 / 128.59 ms │     113.23 / 119.45 ±3.75 / 125.01 ms │     no change │
│ QQuery 37 │        46.69 / 50.98 ±2.22 / 53.10 ms │        47.74 / 49.88 ±1.33 / 51.69 ms │     no change │
│ QQuery 38 │        73.18 / 74.66 ±1.06 / 76.09 ms │        74.66 / 75.19 ±0.77 / 76.71 ms │     no change │
│ QQuery 39 │    202.29 / 216.06 ±10.34 / 230.73 ms │     208.81 / 218.63 ±7.17 / 230.29 ms │     no change │
│ QQuery 40 │        21.58 / 25.17 ±2.12 / 27.60 ms │        22.17 / 24.19 ±1.06 / 25.18 ms │     no change │
│ QQuery 41 │        18.65 / 20.39 ±1.13 / 22.20 ms │        19.80 / 21.02 ±1.06 / 22.76 ms │     no change │
│ QQuery 42 │        18.64 / 19.41 ±0.67 / 20.35 ms │        18.78 / 19.54 ±0.67 / 20.77 ms │     no change │
└───────────┴───────────────────────────────────────┴───────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                 ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                 │ 27157.68ms │
│ Total Time (alamb_morsel_api_2)   │ 26997.05ms │
│ Average Time (HEAD)               │   631.57ms │
│ Average Time (alamb_morsel_api_2) │   627.84ms │
│ Queries Faster                    │          4 │
│ Queries Slower                    │          1 │
│ Queries with No Change            │         38 │
│ Queries with Failure              │          0 │
└───────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric	Value
Wall time	137.0s
Peak memory	39.3 GiB
Avg memory	29.0 GiB
CPU user	1277.8s
CPU sys	101.9s
Disk read	0 B
Disk write	5.5 GiB

clickbench_partitioned — branch

Metric	Value
Wall time	136.2s
Peak memory	44.2 GiB
Avg memory	31.7 GiB
CPU user	1281.1s
CPU sys	91.0s
Disk read	0 B
Disk write	120.0 KiB

File an issue against this benchmark runner

adriangbot · 2026-04-02T21:00:17Z

🤖 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 alamb_morsel_api_2
--------------------
Benchmark tpcds_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┓
┃ Query     ┃                                     HEAD ┃                       alamb_morsel_api_2 ┃       Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━┩
│ QQuery 1  │           43.27 / 43.83 ±0.59 / 44.90 ms │           43.55 / 44.08 ±0.69 / 45.30 ms │    no change │
│ QQuery 2  │        146.55 / 147.24 ±1.08 / 149.39 ms │        147.03 / 148.61 ±0.98 / 150.08 ms │    no change │
│ QQuery 3  │        114.55 / 115.32 ±0.57 / 116.14 ms │        115.08 / 115.98 ±0.80 / 117.14 ms │    no change │
│ QQuery 4  │    1345.89 / 1369.17 ±21.16 / 1399.26 ms │    1328.45 / 1366.03 ±28.99 / 1417.66 ms │    no change │
│ QQuery 5  │        173.74 / 174.81 ±0.89 / 176.14 ms │        173.75 / 175.54 ±1.38 / 177.13 ms │    no change │
│ QQuery 6  │     999.93 / 1020.20 ±13.13 / 1041.33 ms │     976.33 / 1011.96 ±25.35 / 1047.37 ms │    no change │
│ QQuery 7  │        355.81 / 358.48 ±1.51 / 360.51 ms │        355.52 / 357.90 ±1.40 / 359.13 ms │    no change │
│ QQuery 8  │        116.86 / 117.83 ±0.92 / 119.48 ms │        116.94 / 117.78 ±0.48 / 118.26 ms │    no change │
│ QQuery 9  │         96.00 / 103.81 ±4.06 / 106.72 ms │        100.55 / 105.57 ±5.64 / 116.02 ms │    no change │
│ QQuery 10 │        108.25 / 109.76 ±1.53 / 112.70 ms │        109.19 / 111.21 ±1.17 / 112.76 ms │    no change │
│ QQuery 11 │        962.91 / 967.54 ±5.83 / 979.03 ms │       925.91 / 945.19 ±16.14 / 972.89 ms │    no change │
│ QQuery 12 │           45.39 / 46.96 ±0.82 / 47.72 ms │           47.41 / 48.67 ±0.94 / 49.86 ms │    no change │
│ QQuery 13 │        405.21 / 407.26 ±1.35 / 408.80 ms │        405.73 / 409.37 ±3.40 / 415.52 ms │    no change │
│ QQuery 14 │    1019.09 / 1030.98 ±11.26 / 1044.74 ms │     1024.11 / 1029.34 ±5.48 / 1037.89 ms │    no change │
│ QQuery 15 │           16.33 / 16.84 ±0.43 / 17.39 ms │           16.04 / 17.52 ±1.64 / 20.58 ms │    no change │
│ QQuery 16 │           41.07 / 42.21 ±0.96 / 43.51 ms │           41.42 / 43.17 ±1.42 / 45.06 ms │    no change │
│ QQuery 17 │        241.12 / 242.88 ±1.73 / 245.36 ms │        238.97 / 242.37 ±2.99 / 247.17 ms │    no change │
│ QQuery 18 │        129.18 / 130.09 ±0.91 / 131.82 ms │        130.65 / 132.50 ±1.64 / 135.38 ms │    no change │
│ QQuery 19 │        157.17 / 158.17 ±0.61 / 158.82 ms │        156.72 / 158.49 ±1.40 / 160.27 ms │    no change │
│ QQuery 20 │           13.95 / 14.39 ±0.28 / 14.72 ms │           13.86 / 14.42 ±0.48 / 15.01 ms │    no change │
│ QQuery 21 │           19.18 / 19.58 ±0.27 / 19.86 ms │           19.55 / 20.02 ±0.40 / 20.69 ms │    no change │
│ QQuery 22 │        500.15 / 503.98 ±2.59 / 508.17 ms │        484.41 / 486.37 ±1.68 / 488.72 ms │    no change │
│ QQuery 23 │        890.98 / 902.20 ±8.40 / 914.40 ms │        892.66 / 899.37 ±5.15 / 908.16 ms │    no change │
│ QQuery 24 │        421.36 / 423.83 ±1.87 / 427.06 ms │        417.16 / 419.61 ±1.63 / 422.28 ms │    no change │
│ QQuery 25 │        357.25 / 361.40 ±2.51 / 364.71 ms │        354.06 / 356.38 ±1.46 / 358.31 ms │    no change │
│ QQuery 26 │           81.12 / 83.35 ±1.75 / 86.09 ms │           82.43 / 84.77 ±1.50 / 86.45 ms │    no change │
│ QQuery 27 │        351.57 / 356.69 ±2.56 / 358.18 ms │        353.15 / 355.90 ±1.87 / 357.71 ms │    no change │
│ QQuery 28 │        151.00 / 152.53 ±1.34 / 154.77 ms │        149.69 / 151.13 ±1.17 / 152.75 ms │    no change │
│ QQuery 29 │        302.67 / 305.06 ±2.12 / 308.79 ms │        296.89 / 300.73 ±3.24 / 304.62 ms │    no change │
│ QQuery 30 │           44.39 / 45.34 ±0.79 / 46.58 ms │           44.76 / 46.52 ±1.27 / 48.18 ms │    no change │
│ QQuery 31 │        174.09 / 177.02 ±1.97 / 179.31 ms │        172.61 / 173.91 ±0.92 / 175.24 ms │    no change │
│ QQuery 32 │           56.87 / 58.01 ±1.13 / 60.17 ms │           57.67 / 58.56 ±0.82 / 59.83 ms │    no change │
│ QQuery 33 │        142.00 / 143.92 ±1.73 / 146.86 ms │        140.69 / 143.04 ±1.79 / 146.10 ms │    no change │
│ QQuery 34 │        108.61 / 109.70 ±0.67 / 110.48 ms │        106.97 / 108.58 ±1.03 / 109.85 ms │    no change │
│ QQuery 35 │        108.55 / 110.27 ±1.38 / 111.57 ms │        109.66 / 110.47 ±0.55 / 111.32 ms │    no change │
│ QQuery 36 │        218.44 / 220.99 ±1.97 / 224.23 ms │        218.09 / 220.92 ±2.06 / 222.95 ms │    no change │
│ QQuery 37 │        177.36 / 179.98 ±2.20 / 183.58 ms │        175.84 / 178.11 ±1.38 / 179.95 ms │    no change │
│ QQuery 38 │           84.80 / 87.98 ±1.76 / 89.98 ms │           84.30 / 88.96 ±4.69 / 96.21 ms │    no change │
│ QQuery 39 │        125.42 / 130.26 ±2.68 / 133.54 ms │        126.07 / 127.89 ±2.11 / 132.01 ms │    no change │
│ QQuery 40 │        111.25 / 118.17 ±6.88 / 130.13 ms │        113.07 / 117.94 ±4.31 / 124.65 ms │    no change │
│ QQuery 41 │           14.75 / 15.39 ±0.46 / 16.00 ms │           14.27 / 15.66 ±1.05 / 17.27 ms │    no change │
│ QQuery 42 │        108.98 / 110.53 ±0.93 / 111.63 ms │        107.22 / 108.73 ±1.90 / 112.33 ms │    no change │
│ QQuery 43 │           84.15 / 84.96 ±0.63 / 86.04 ms │           84.91 / 85.81 ±0.69 / 86.87 ms │    no change │
│ QQuery 44 │           11.59 / 11.88 ±0.25 / 12.32 ms │           11.74 / 12.32 ±0.66 / 13.50 ms │    no change │
│ QQuery 45 │           54.00 / 54.83 ±0.53 / 55.56 ms │           52.38 / 53.84 ±1.11 / 55.70 ms │    no change │
│ QQuery 46 │        230.54 / 234.97 ±2.44 / 237.35 ms │        233.87 / 235.93 ±1.16 / 237.25 ms │    no change │
│ QQuery 47 │        703.84 / 712.94 ±5.47 / 719.42 ms │        705.08 / 710.52 ±3.85 / 714.94 ms │    no change │
│ QQuery 48 │        285.69 / 290.86 ±3.10 / 295.17 ms │        295.29 / 298.21 ±2.90 / 302.82 ms │    no change │
│ QQuery 49 │        257.07 / 258.73 ±1.11 / 259.77 ms │        256.80 / 258.93 ±1.62 / 260.76 ms │    no change │
│ QQuery 50 │        235.70 / 237.58 ±1.04 / 238.86 ms │        233.09 / 236.03 ±2.59 / 239.88 ms │    no change │
│ QQuery 51 │        181.80 / 185.82 ±2.55 / 189.10 ms │        183.70 / 187.70 ±3.11 / 191.09 ms │    no change │
│ QQuery 52 │        108.59 / 109.60 ±0.98 / 111.17 ms │        107.70 / 109.86 ±1.70 / 112.38 ms │    no change │
│ QQuery 53 │        104.06 / 105.17 ±0.86 / 106.22 ms │        103.86 / 104.45 ±0.69 / 105.70 ms │    no change │
│ QQuery 54 │        148.25 / 150.63 ±1.48 / 152.52 ms │        147.99 / 150.14 ±1.71 / 152.64 ms │    no change │
│ QQuery 55 │        107.18 / 108.38 ±0.86 / 109.28 ms │        108.04 / 109.86 ±1.48 / 112.37 ms │    no change │
│ QQuery 56 │        140.36 / 142.65 ±1.66 / 144.95 ms │        142.52 / 143.14 ±1.09 / 145.31 ms │    no change │
│ QQuery 57 │        173.69 / 175.60 ±1.73 / 178.20 ms │        178.70 / 179.68 ±1.01 / 181.43 ms │    no change │
│ QQuery 58 │        295.00 / 299.15 ±3.33 / 303.35 ms │        292.56 / 302.45 ±8.75 / 316.32 ms │    no change │
│ QQuery 59 │        198.79 / 201.90 ±1.68 / 203.91 ms │        202.73 / 204.11 ±0.74 / 204.81 ms │    no change │
│ QQuery 60 │        144.78 / 145.39 ±0.97 / 147.32 ms │        144.19 / 145.58 ±1.02 / 146.57 ms │    no change │
│ QQuery 61 │        170.44 / 172.05 ±1.57 / 174.00 ms │        171.05 / 173.53 ±1.92 / 176.92 ms │    no change │
│ QQuery 62 │      885.95 / 926.98 ±48.85 / 1021.81 ms │      936.23 / 963.74 ±21.39 / 1001.77 ms │    no change │
│ QQuery 63 │        104.78 / 107.42 ±2.19 / 111.04 ms │        105.42 / 108.54 ±2.32 / 112.58 ms │    no change │
│ QQuery 64 │        706.64 / 711.81 ±5.01 / 721.40 ms │        719.49 / 726.88 ±4.12 / 730.37 ms │    no change │
│ QQuery 65 │        254.81 / 258.54 ±2.21 / 261.43 ms │        263.89 / 266.20 ±1.57 / 268.12 ms │    no change │
│ QQuery 66 │       231.68 / 247.38 ±11.76 / 265.15 ms │        251.99 / 262.62 ±9.30 / 275.38 ms │ 1.06x slower │
│ QQuery 67 │        313.84 / 321.41 ±5.89 / 331.76 ms │        326.17 / 328.03 ±1.29 / 329.73 ms │    no change │
│ QQuery 68 │        283.23 / 286.44 ±3.82 / 293.28 ms │        292.20 / 297.54 ±5.89 / 308.49 ms │    no change │
│ QQuery 69 │        103.83 / 104.94 ±1.76 / 108.42 ms │        104.19 / 106.68 ±1.97 / 109.90 ms │    no change │
│ QQuery 70 │        342.42 / 346.28 ±3.06 / 350.08 ms │        340.96 / 350.80 ±9.42 / 365.63 ms │    no change │
│ QQuery 71 │        136.81 / 138.89 ±1.82 / 141.81 ms │        137.20 / 139.16 ±2.61 / 144.22 ms │    no change │
│ QQuery 72 │       712.92 / 728.40 ±11.87 / 742.51 ms │       720.83 / 754.10 ±19.38 / 778.15 ms │    no change │
│ QQuery 73 │        104.21 / 106.05 ±1.76 / 108.87 ms │        104.98 / 106.61 ±2.17 / 110.83 ms │    no change │
│ QQuery 74 │        603.52 / 613.09 ±7.73 / 626.60 ms │       578.13 / 611.08 ±26.64 / 639.55 ms │    no change │
│ QQuery 75 │        276.27 / 280.81 ±2.62 / 283.82 ms │        278.91 / 281.57 ±2.04 / 284.61 ms │    no change │
│ QQuery 76 │        134.09 / 136.47 ±1.22 / 137.38 ms │        135.92 / 136.98 ±1.58 / 140.06 ms │    no change │
│ QQuery 77 │        188.67 / 190.80 ±1.55 / 192.84 ms │        190.73 / 192.71 ±1.99 / 195.35 ms │    no change │
│ QQuery 78 │        352.88 / 358.37 ±4.12 / 362.33 ms │        362.51 / 368.06 ±5.19 / 376.74 ms │    no change │
│ QQuery 79 │        233.90 / 235.94 ±1.84 / 238.73 ms │        244.47 / 246.75 ±1.25 / 247.85 ms │    no change │
│ QQuery 80 │        333.59 / 336.58 ±1.55 / 337.97 ms │        331.48 / 336.93 ±3.48 / 341.49 ms │    no change │
│ QQuery 81 │           27.05 / 28.57 ±0.86 / 29.70 ms │           27.14 / 28.70 ±1.33 / 30.51 ms │    no change │
│ QQuery 82 │        200.34 / 202.91 ±2.54 / 207.37 ms │        200.39 / 202.88 ±1.33 / 203.95 ms │    no change │
│ QQuery 83 │           41.21 / 42.03 ±0.57 / 42.80 ms │           40.75 / 41.37 ±0.60 / 42.35 ms │    no change │
│ QQuery 84 │           49.28 / 50.83 ±1.40 / 52.92 ms │           48.88 / 50.38 ±1.19 / 52.45 ms │    no change │
│ QQuery 85 │        152.00 / 152.47 ±0.40 / 153.07 ms │        151.92 / 153.59 ±1.60 / 156.08 ms │    no change │
│ QQuery 86 │           39.38 / 40.60 ±0.97 / 42.04 ms │           39.62 / 40.53 ±0.90 / 42.19 ms │    no change │
│ QQuery 87 │           88.62 / 92.29 ±3.15 / 96.62 ms │           86.46 / 89.78 ±3.05 / 95.41 ms │    no change │
│ QQuery 88 │        100.94 / 102.04 ±0.88 / 103.26 ms │        101.03 / 102.11 ±1.26 / 104.56 ms │    no change │
│ QQuery 89 │        120.33 / 121.33 ±0.97 / 123.04 ms │        117.96 / 119.89 ±1.12 / 121.45 ms │    no change │
│ QQuery 90 │           23.88 / 25.23 ±1.18 / 26.83 ms │           23.55 / 24.06 ±0.45 / 24.86 ms │    no change │
│ QQuery 91 │           62.93 / 64.80 ±1.47 / 66.92 ms │           64.11 / 65.25 ±1.08 / 67.02 ms │    no change │
│ QQuery 92 │           57.88 / 58.85 ±0.63 / 59.71 ms │           57.34 / 57.98 ±0.60 / 58.98 ms │    no change │
│ QQuery 93 │        193.84 / 195.62 ±1.39 / 198.07 ms │        192.62 / 194.80 ±1.79 / 197.01 ms │    no change │
│ QQuery 94 │           61.91 / 62.75 ±1.04 / 64.72 ms │           60.43 / 61.25 ±0.99 / 63.11 ms │    no change │
│ QQuery 95 │        134.68 / 136.31 ±0.84 / 136.96 ms │        133.69 / 136.03 ±1.45 / 138.24 ms │    no change │
│ QQuery 96 │           72.95 / 74.10 ±1.03 / 75.31 ms │           70.00 / 73.31 ±1.88 / 75.27 ms │    no change │
│ QQuery 97 │        128.28 / 132.65 ±2.65 / 135.51 ms │        129.93 / 131.10 ±1.09 / 132.75 ms │    no change │
│ QQuery 98 │        154.78 / 158.15 ±2.40 / 160.68 ms │        156.02 / 157.82 ±1.57 / 160.20 ms │    no change │
│ QQuery 99 │ 10809.29 / 10842.80 ±20.46 / 10865.12 ms │ 10782.90 / 10810.84 ±18.33 / 10834.72 ms │    no change │
└───────────┴──────────────────────────────────────────┴──────────────────────────────────────────┴──────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                 ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                 │ 33938.01ms │
│ Total Time (alamb_morsel_api_2)   │ 33998.02ms │
│ Average Time (HEAD)               │   342.81ms │
│ Average Time (alamb_morsel_api_2) │   343.41ms │
│ 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	170.0s
Peak memory	5.8 GiB
Avg memory	4.8 GiB
CPU user	273.4s
CPU sys	18.2s
Disk read	0 B
Disk write	703.4 MiB

tpcds — branch

Metric	Value
Wall time	170.3s
Peak memory	5.7 GiB
Avg memory	4.7 GiB
CPU user	274.0s
CPU sys	18.5s
Disk read	0 B
Disk write	576.0 KiB

File an issue against this benchmark runner

adriangbot · 2026-04-02T21:01:18Z

🤖 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 alamb_morsel_api_2
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃                    alamb_morsel_api_2 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.30 / 4.66 ±6.54 / 17.73 ms │          1.33 / 4.61 ±6.42 / 17.46 ms │     no change │
│ QQuery 1  │        14.35 / 14.88 ±0.28 / 15.10 ms │        14.92 / 15.43 ±0.27 / 15.73 ms │     no change │
│ QQuery 2  │        44.55 / 44.98 ±0.32 / 45.54 ms │        45.03 / 45.18 ±0.10 / 45.33 ms │     no change │
│ QQuery 3  │        43.06 / 45.47 ±1.68 / 48.05 ms │        42.43 / 44.77 ±1.98 / 47.31 ms │     no change │
│ QQuery 4  │     305.27 / 312.94 ±7.96 / 327.47 ms │     291.49 / 300.73 ±8.43 / 314.72 ms │     no change │
│ QQuery 5  │     356.04 / 358.19 ±2.93 / 364.00 ms │     350.52 / 353.31 ±2.40 / 357.55 ms │     no change │
│ QQuery 6  │           6.14 / 7.21 ±1.11 / 9.09 ms │           5.58 / 6.71 ±0.77 / 7.66 ms │ +1.07x faster │
│ QQuery 7  │        17.27 / 17.44 ±0.09 / 17.53 ms │        17.29 / 17.83 ±0.29 / 18.17 ms │     no change │
│ QQuery 8  │    429.50 / 450.95 ±16.81 / 473.07 ms │     428.96 / 437.88 ±8.30 / 448.61 ms │     no change │
│ QQuery 9  │     683.81 / 692.36 ±4.90 / 697.78 ms │     659.07 / 666.34 ±6.01 / 674.35 ms │     no change │
│ QQuery 10 │        92.64 / 94.30 ±1.46 / 96.76 ms │        92.42 / 95.19 ±2.62 / 99.51 ms │     no change │
│ QQuery 11 │     106.17 / 107.42 ±0.90 / 108.49 ms │     104.59 / 106.99 ±1.68 / 109.56 ms │     no change │
│ QQuery 12 │     361.98 / 366.16 ±3.79 / 373.01 ms │     347.72 / 352.40 ±3.53 / 357.80 ms │     no change │
│ QQuery 13 │     491.42 / 499.79 ±9.70 / 515.00 ms │    448.91 / 474.95 ±21.51 / 511.83 ms │     no change │
│ QQuery 14 │     358.59 / 364.66 ±4.05 / 369.31 ms │     353.15 / 359.44 ±3.70 / 364.36 ms │     no change │
│ QQuery 15 │    372.00 / 392.73 ±23.82 / 431.84 ms │    385.31 / 403.29 ±17.40 / 429.93 ms │     no change │
│ QQuery 16 │    731.24 / 742.98 ±10.38 / 761.34 ms │    747.85 / 767.73 ±18.54 / 802.52 ms │     no change │
│ QQuery 17 │    732.11 / 754.49 ±25.59 / 800.38 ms │     725.44 / 735.03 ±5.44 / 740.89 ms │     no change │
│ QQuery 18 │ 1475.82 / 1505.00 ±17.10 / 1521.23 ms │ 1471.10 / 1508.22 ±23.21 / 1534.48 ms │     no change │
│ QQuery 19 │       35.61 / 43.29 ±12.51 / 68.18 ms │        35.81 / 37.65 ±1.93 / 41.05 ms │ +1.15x faster │
│ QQuery 20 │    712.35 / 732.71 ±20.75 / 766.34 ms │    714.63 / 728.35 ±16.94 / 760.38 ms │     no change │
│ QQuery 21 │     760.36 / 766.12 ±3.40 / 770.65 ms │     760.40 / 765.16 ±2.94 / 768.55 ms │     no change │
│ QQuery 22 │  1131.45 / 1137.95 ±6.52 / 1147.86 ms │  1133.91 / 1137.14 ±3.57 / 1143.41 ms │     no change │
│ QQuery 23 │ 3087.97 / 3113.00 ±13.20 / 3125.70 ms │  3118.81 / 3128.20 ±8.73 / 3139.60 ms │     no change │
│ QQuery 24 │     100.42 / 102.73 ±2.28 / 106.71 ms │     101.48 / 104.58 ±1.72 / 106.75 ms │     no change │
│ QQuery 25 │     138.25 / 141.96 ±2.68 / 145.86 ms │     140.37 / 142.92 ±2.12 / 145.75 ms │     no change │
│ QQuery 26 │      98.53 / 101.38 ±1.92 / 104.21 ms │     101.06 / 103.40 ±1.65 / 105.06 ms │     no change │
│ QQuery 27 │     847.19 / 855.51 ±9.14 / 872.72 ms │    844.61 / 855.26 ±13.31 / 881.42 ms │     no change │
│ QQuery 28 │ 7832.94 / 7876.37 ±26.13 / 7901.79 ms │ 7725.82 / 7801.19 ±41.38 / 7840.26 ms │     no change │
│ QQuery 29 │        51.08 / 53.85 ±3.80 / 61.12 ms │        50.69 / 55.56 ±3.02 / 59.59 ms │     no change │
│ QQuery 30 │     366.57 / 375.87 ±5.40 / 381.82 ms │     374.94 / 383.35 ±6.54 / 390.57 ms │     no change │
│ QQuery 31 │     370.11 / 382.39 ±8.97 / 394.38 ms │     391.00 / 402.35 ±6.91 / 412.66 ms │  1.05x slower │
│ QQuery 32 │ 1282.76 / 1341.58 ±48.78 / 1428.29 ms │ 1219.81 / 1312.17 ±61.14 / 1412.78 ms │     no change │
│ QQuery 33 │ 1467.04 / 1527.86 ±44.18 / 1598.70 ms │ 1645.95 / 1653.15 ±10.90 / 1674.73 ms │  1.08x slower │
│ QQuery 34 │ 1479.49 / 1494.81 ±16.21 / 1524.56 ms │ 1491.44 / 1553.75 ±55.56 / 1626.36 ms │     no change │
│ QQuery 35 │     401.41 / 404.49 ±1.70 / 406.46 ms │     399.82 / 408.30 ±6.40 / 416.66 ms │     no change │
│ QQuery 36 │     117.71 / 122.93 ±3.20 / 126.86 ms │     116.50 / 120.20 ±2.59 / 123.74 ms │     no change │
│ QQuery 37 │        50.18 / 51.93 ±1.34 / 53.49 ms │        48.82 / 51.61 ±3.65 / 58.74 ms │     no change │
│ QQuery 38 │        75.11 / 76.97 ±1.54 / 79.61 ms │        74.79 / 76.19 ±1.14 / 77.29 ms │     no change │
│ QQuery 39 │     210.32 / 222.33 ±8.83 / 233.67 ms │    207.86 / 221.78 ±10.87 / 236.09 ms │     no change │
│ QQuery 40 │        26.50 / 28.01 ±1.05 / 29.38 ms │        22.73 / 25.16 ±1.53 / 27.08 ms │ +1.11x faster │
│ QQuery 41 │        19.00 / 20.34 ±0.87 / 21.64 ms │        22.10 / 22.61 ±0.44 / 23.35 ms │  1.11x slower │
│ QQuery 42 │        20.11 / 20.69 ±0.88 / 22.40 ms │        19.08 / 20.05 ±0.54 / 20.68 ms │     no change │
└───────────┴───────────────────────────────────────┴───────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                 ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                 │ 27771.67ms │
│ Total Time (alamb_morsel_api_2)   │ 27806.14ms │
│ Average Time (HEAD)               │   645.85ms │
│ Average Time (alamb_morsel_api_2) │   646.65ms │
│ Queries Faster                    │          3 │
│ Queries Slower                    │          3 │
│ Queries with No Change            │         37 │
│ Queries with Failure              │          0 │
└───────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric	Value
Wall time	140.1s
Peak memory	41.9 GiB
Avg memory	29.7 GiB
CPU user	1304.9s
CPU sys	105.0s
Disk read	0 B
Disk write	3.1 GiB

clickbench_partitioned — branch

Metric	Value
Wall time	140.2s
Peak memory	40.0 GiB
Avg memory	31.3 GiB
CPU user	1300.6s
CPU sys	109.2s
Disk read	0 B
Disk write	120.0 KiB

File an issue against this benchmark runner

Dandandan · 2026-04-03T04:55:33Z

I like how small the PR is!

alamb · 2026-04-03T16:02:05Z

I like how small the PR is!

Though it it doesn't do anything useful yet :)

Introduce Morselizer API

9d4457c

github-actions bot added the datasource Changes to the datasource crate label Apr 2, 2026

alamb mentioned this pull request Apr 3, 2026

Rewrite FileStream in terms of Morsel API #21342

Draft

alamb mentioned this pull request Apr 3, 2026

Dynamic work scheduling in FileStream #21351

Draft

Conversation

alamb commented Apr 2, 2026

Which issue does this PR close?

Rationale for this change

What changes are included in this PR?

Are these changes tested?

Are there any user-facing changes?

Uh oh!

alamb commented Apr 2, 2026

Uh oh!

alamb commented Apr 2, 2026

Uh oh!

alamb commented Apr 2, 2026

Uh oh!

adriangbot commented Apr 2, 2026

Uh oh!

adriangbot commented Apr 2, 2026

Uh oh!

adriangbot commented Apr 2, 2026

Uh oh!

adriangbot commented Apr 2, 2026

Uh oh!

adriangbot commented Apr 2, 2026

Uh oh!

adriangb commented Apr 2, 2026

Uh oh!

adriangbot commented Apr 2, 2026

Uh oh!

adriangbot commented Apr 2, 2026

Uh oh!

adriangbot commented Apr 2, 2026

Uh oh!

adriangbot commented Apr 2, 2026

Uh oh!

adriangbot commented Apr 2, 2026

Uh oh!

Dandandan commented Apr 3, 2026

Uh oh!

alamb commented Apr 3, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants