Skip to content

chore: Update to arrow/parquet 59.0.0#22744

Draft
alamb wants to merge 2 commits into
apache:mainfrom
alamb:alamb/update_arrow_59
Draft

chore: Update to arrow/parquet 59.0.0#22744
alamb wants to merge 2 commits into
apache:mainfrom
alamb:alamb/update_arrow_59

Conversation

@alamb
Copy link
Copy Markdown
Contributor

@alamb alamb commented Jun 3, 2026

Which issue does this PR close?

WIP: I am using this PR to test the arrow release

Rationale for this change

Update to latest version of arrow/parquet

What changes are included in this PR?

  1. Update to arrow/parquet 59.0.0
  2. Adjust code for API differences

Are these changes tested?

By CI

Are there any user-facing changes?

New dependency

@github-actions github-actions Bot added physical-expr Changes to the physical-expr crates core Core DataFusion crate common Related to common crate datasource Changes to the datasource crate physical-plan Changes to the physical-plan crate spark labels Jun 3, 2026
.bloom_filter_properties(&ColumnPath::from(""))
.expect("expected bloom properties!")
.fpp,
.fpp(),
Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

};
if let Some(bloom_filter_ndv) = bloom_filter_ndv {
builder = builder.set_bloom_filter_ndv(*bloom_filter_ndv);
builder = builder.set_bloom_filter_max_ndv(*bloom_filter_ndv);
Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ndv: DEFAULT_BLOOM_FILTER_NDV
}),
Some(
&BloomFilterProperties::builder()
Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

&[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
&[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 0, 1, 2, 3, 5, 6],
]))],
vec![Arc::new(
Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

scale: 2,
precision: 9,
})
.with_logical_type(LogicalType::decimal(2, 9))
Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Comment thread Cargo.lock
]

[[package]]
name = "integer-encoding"
Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yay for removing older deps

Comment thread Cargo.lock
"cfg-if",
]

[[package]]
Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

no more thrift! We now use the entirely new thrift encoder and not the thrift generator

@github-actions
Copy link
Copy Markdown

github-actions Bot commented Jun 3, 2026

Thank you for opening this pull request!

Reviewer note: cargo-semver-checks reported the current version number is not SemVer-compatible with the changes in this pull request (compared against the base branch).

Details
     Cloning apache/main
error: running 'cargo update' on crate 'datafusion' failed with output:
-----
    Updating crates.io index
error: failed to select a version for the requirement `arrow = "^59.0.0"`
candidate versions found which didn't match: 58.3.0, 58.2.0, 58.1.0, ...
location searched: crates.io index
required by package `datafusion v53.1.0 (/home/runner/work/datafusion/datafusion/datafusion/core)`
    ... which satisfies path dependency `datafusion` of package `placeholder v0.0.0 (/home/runner/work/datafusion/datafusion/target/semver-checks/local-datafusion-53_1_0-x86_64_unknown_linux_gnu-1b7914a76ab5b0e9)`

-----
error: failed to update dependencies for crate datafusion v53.1.0
note: this is unlikely to be a bug in cargo-semver-checks,
      and is probably an issue with the crate's Cargo.toml
note: the following command can be used to reproduce the compilation error:
      cargo new --lib example &&
          cd example &&
          echo '[workspace]' >> Cargo.toml &&
          cargo add --path /home/runner/work/datafusion/datafusion/datafusion/core --features array_expressions,avro,backtrace,bzip2,compression,crypto_expressions,datafusion-datasource-avro,datafusion-datasource-parquet,datafusion-functions-nested,datafusion-sql,datetime_expressions,default,encoding_expressions,extended_tests,flate2,force_hash_collisions,liblzma,math_expressions,nested_expressions,parquet,parquet_encryption,recursive_protection,regex_expressions,serde,sql,sqlparser,string_expressions,unicode_expressions,zstd &&
          cargo update

error: running 'cargo update' on crate 'datafusion-cli' failed with output:
-----
    Updating crates.io index
error: failed to select a version for the requirement `arrow = "^59.0.0"`
candidate versions found which didn't match: 58.3.0, 58.2.0, 58.1.0, ...
location searched: crates.io index
required by package `datafusion-cli v53.1.0 (/home/runner/work/datafusion/datafusion/datafusion-cli)`
    ... which satisfies path dependency `datafusion-cli` of package `placeholder v0.0.0 (/home/runner/work/datafusion/datafusion/target/semver-checks/local-datafusion_cli-53_1_0-x86_64_unknown_linux_gnu-b32879924fd93411)`

-----
error: failed to update dependencies for crate datafusion-cli v53.1.0
note: this is unlikely to be a bug in cargo-semver-checks,
      and is probably an issue with the crate's Cargo.toml
note: the following command can be used to reproduce the compilation error:
      cargo new --lib example &&
          cd example &&
          echo '[workspace]' >> Cargo.toml &&
          cargo add --path /home/runner/work/datafusion/datafusion/datafusion-cli --features backtrace,default &&
          cargo update

error: running 'cargo update' on crate 'datafusion-common' failed with output:
-----
    Updating crates.io index
error: failed to select a version for the requirement `arrow = "^59.0.0"`
candidate versions found which didn't match: 58.3.0, 58.2.0, 58.1.0, ...
location searched: crates.io index
required by package `datafusion-common v53.1.0 (/home/runner/work/datafusion/datafusion/datafusion/common)`
    ... which satisfies path dependency `datafusion-common` of package `placeholder v0.0.0 (/home/runner/work/datafusion/datafusion/target/semver-checks/local-datafusion_common-53_1_0-x86_64_unknown_linux_gnu-aacf76e6b0db3a79)`

-----
error: failed to update dependencies for crate datafusion-common v53.1.0
note: this is unlikely to be a bug in cargo-semver-checks,
      and is probably an issue with the crate's Cargo.toml
note: the following command can be used to reproduce the compilation error:
      cargo new --lib example &&
          cd example &&
          echo '[workspace]' >> Cargo.toml &&
          cargo add --path /home/runner/work/datafusion/datafusion/datafusion/common --features backtrace,force_hash_collisions,object_store,parquet,parquet_encryption,recursive_protection,sql,sqlparser &&
          cargo update

error: running 'cargo update' on crate 'datafusion-datasource-parquet' failed with output:
-----
    Updating crates.io index
error: failed to select a version for the requirement `arrow = "^59.0.0"`
candidate versions found which didn't match: 58.3.0, 58.2.0, 58.1.0, ...
location searched: crates.io index
required by package `datafusion-datasource-parquet v53.1.0 (/home/runner/work/datafusion/datafusion/datafusion/datasource-parquet)`
    ... which satisfies path dependency `datafusion-datasource-parquet` of package `placeholder v0.0.0 (/home/runner/work/datafusion/datafusion/target/semver-checks/local-datafusion_datasource_parquet-53_1_0-x86_64_unknown_linux_gnu-04f8f2cef0155602)`

-----
error: failed to update dependencies for crate datafusion-datasource-parquet v53.1.0
note: this is unlikely to be a bug in cargo-semver-checks,
      and is probably an issue with the crate's Cargo.toml
note: the following command can be used to reproduce the compilation error:
      cargo new --lib example &&
          cd example &&
          echo '[workspace]' >> Cargo.toml &&
          cargo add --path /home/runner/work/datafusion/datafusion/datafusion/datasource-parquet --features parquet_encryption &&
          cargo update

error: running 'cargo update' on crate 'datafusion-physical-expr' failed with output:
-----
    Updating crates.io index
error: failed to select a version for the requirement `arrow = "^59.0.0"`
candidate versions found which didn't match: 58.3.0, 58.2.0, 58.1.0, ...
location searched: crates.io index
required by package `datafusion-physical-expr v53.1.0 (/home/runner/work/datafusion/datafusion/datafusion/physical-expr)`
    ... which satisfies path dependency `datafusion-physical-expr` of package `placeholder v0.0.0 (/home/runner/work/datafusion/datafusion/target/semver-checks/local-datafusion_physical_expr-53_1_0-x86_64_unknown_linux_gnu-bca8e229768be254)`

-----
error: failed to update dependencies for crate datafusion-physical-expr v53.1.0
note: this is unlikely to be a bug in cargo-semver-checks,
      and is probably an issue with the crate's Cargo.toml
note: the following command can be used to reproduce the compilation error:
      cargo new --lib example &&
          cd example &&
          echo '[workspace]' >> Cargo.toml &&
          cargo add --path /home/runner/work/datafusion/datafusion/datafusion/physical-expr --features proto,recursive_protection &&
          cargo update

error: running 'cargo update' on crate 'datafusion-physical-expr-common' failed with output:
-----
    Updating crates.io index
error: failed to select a version for the requirement `arrow = "^59.0.0"`
candidate versions found which didn't match: 58.3.0, 58.2.0, 58.1.0, ...
location searched: crates.io index
required by package `datafusion-physical-expr-common v53.1.0 (/home/runner/work/datafusion/datafusion/datafusion/physical-expr-common)`
    ... which satisfies path dependency `datafusion-physical-expr-common` of package `placeholder v0.0.0 (/home/runner/work/datafusion/datafusion/target/semver-checks/local-datafusion_physical_expr_common-53_1_0-x86_64_unknown_linux_gnu-e520032dc2e44efb)`

-----
error: failed to update dependencies for crate datafusion-physical-expr-common v53.1.0
note: this is unlikely to be a bug in cargo-semver-checks,
      and is probably an issue with the crate's Cargo.toml
note: the following command can be used to reproduce the compilation error:
      cargo new --lib example &&
          cd example &&
          echo '[workspace]' >> Cargo.toml &&
          cargo add --path /home/runner/work/datafusion/datafusion/datafusion/physical-expr-common --features default,proto &&
          cargo update

error: running 'cargo update' on crate 'datafusion-physical-plan' failed with output:
-----
    Updating crates.io index
error: failed to select a version for the requirement `arrow = "^59.0.0"`
candidate versions found which didn't match: 58.3.0, 58.2.0, 58.1.0, ...
location searched: crates.io index
required by package `datafusion-physical-plan v53.1.0 (/home/runner/work/datafusion/datafusion/datafusion/physical-plan)`
    ... which satisfies path dependency `datafusion-physical-plan` of package `placeholder v0.0.0 (/home/runner/work/datafusion/datafusion/target/semver-checks/local-datafusion_physical_plan-53_1_0-x86_64_unknown_linux_gnu-1f91daf2459157c5)`

-----
error: failed to update dependencies for crate datafusion-physical-plan v53.1.0
note: this is unlikely to be a bug in cargo-semver-checks,
      and is probably an issue with the crate's Cargo.toml
note: the following command can be used to reproduce the compilation error:
      cargo new --lib example &&
          cd example &&
          echo '[workspace]' >> Cargo.toml &&
          cargo add --path /home/runner/work/datafusion/datafusion/datafusion/physical-plan --features force_hash_collisions,proto,test_utils,tokio_coop,tokio_coop_fallback &&
          cargo update

error: running 'cargo update' on crate 'datafusion-spark' failed with output:
-----
    Updating crates.io index
error: failed to select a version for the requirement `arrow = "^59.0.0"`
candidate versions found which didn't match: 58.3.0, 58.2.0, 58.1.0, ...
location searched: crates.io index
required by package `datafusion-spark v53.1.0 (/home/runner/work/datafusion/datafusion/datafusion/spark)`
    ... which satisfies path dependency `datafusion-spark` of package `placeholder v0.0.0 (/home/runner/work/datafusion/datafusion/target/semver-checks/local-datafusion_spark-53_1_0-x86_64_unknown_linux_gnu-353fa9c28778b101)`

-----
error: failed to update dependencies for crate datafusion-spark v53.1.0
note: this is unlikely to be a bug in cargo-semver-checks,
      and is probably an issue with the crate's Cargo.toml
note: the following command can be used to reproduce the compilation error:
      cargo new --lib example &&
          cd example &&
          echo '[workspace]' >> Cargo.toml &&
          cargo add --path /home/runner/work/datafusion/datafusion/datafusion/spark --features core,datafusion,default &&
          cargo update

error: aborting due to failure to run 'cargo update' for crate datafusion v53.1.0

@github-actions github-actions Bot added the auto detected api change Auto detected API change label Jun 3, 2026
@alamb alamb force-pushed the alamb/update_arrow_59 branch from 55c7eb3 to e616241 Compare June 4, 2026 11:13
| alltypes_plain.parquet | 1851 | 8882 | 2 | page_index=false |
| alltypes_tiny_pages.parquet | 454233 | 269074 | 2 | page_index=true |
| lz4_raw_compressed_larger.parquet | 380836 | 1339 | 2 | page_index=false |
| alltypes_plain.parquet | 1851 | 8794 | 2 | page_index=false |
Copy link
Copy Markdown
Contributor Author

@alamb alamb Jun 4, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this changed (smaller in memory size) due to the representation change of CompressionCodec in this pr

It changes from Compression which also carries the compression level: ZSTD(ZstdLevel), GZIP(GzipLevel), BROTLI(BrotliLevel) — and ZstdLevel(i32) / GzipLevel(u32) / BrotliLevel(u32) and are 4-byte wrappers. So Compression = 4-byte discriminant + 4-byte level = 8 bytes.

To a fieldless enum CompressionCodec -- 1 byte

Total Requests: 2
- GET (opts) path=parquet_table.parquet head=true
- GET (ranges) path=parquet_table.parquet ranges=1064-1481,1481-1594,1594-2011,2011-2124
- GET (ranges) path=parquet_table.parquet ranges=1064-1594,1594-2124
Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this seems like an improvement -- contiguous ranges are coalesced into fewer ranges. I tracked it down to this PR from @HippoBaro

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Music to my hears!

@alamb alamb force-pushed the alamb/update_arrow_59 branch from e616241 to 4d274ef Compare June 4, 2026 18:09
@alamb
Copy link
Copy Markdown
Contributor Author

alamb commented Jun 4, 2026

run benchmarks

@adriangbot
Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4624884915-444-rzk79 6.12.68+ #1 SMP Wed Apr 1 02:23:28 UTC 2026 aarch64 GNU/Linux

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

Comparing alamb/update_arrow_59 (4d274ef) to 18e7c8e (merge-base) diff using: tpch
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot
Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4624884915-443-xp9xx 6.12.68+ #1 SMP Wed Apr 1 02:23:28 UTC 2026 aarch64 GNU/Linux

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

Comparing alamb/update_arrow_59 (4d274ef) to 18e7c8e (merge-base) diff using: tpcds
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot
Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4624884915-442-zdpqw 6.12.68+ #1 SMP Wed Apr 1 02:23:28 UTC 2026 aarch64 GNU/Linux

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

Comparing alamb/update_arrow_59 (4d274ef) to 18e7c8e (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot
Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

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

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

Comparing HEAD and alamb_update_arrow_59
--------------------
Benchmark tpch_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                           HEAD ┃          alamb_update_arrow_59 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1  │ 38.69 / 40.91 ±2.54 / 45.14 ms │ 38.33 / 39.68 ±1.54 / 41.61 ms │     no change │
│ QQuery 2  │ 18.65 / 18.91 ±0.28 / 19.31 ms │ 18.74 / 18.85 ±0.13 / 19.10 ms │     no change │
│ QQuery 3  │ 31.05 / 32.97 ±1.30 / 34.40 ms │ 31.22 / 32.73 ±1.23 / 34.04 ms │     no change │
│ QQuery 4  │ 17.56 / 18.20 ±0.51 / 18.75 ms │ 17.35 / 17.42 ±0.08 / 17.58 ms │     no change │
│ QQuery 5  │ 37.55 / 39.66 ±1.67 / 41.25 ms │ 37.88 / 41.33 ±2.24 / 43.83 ms │     no change │
│ QQuery 6  │ 16.27 / 17.14 ±0.93 / 18.84 ms │ 16.11 / 16.43 ±0.38 / 17.16 ms │     no change │
│ QQuery 7  │ 44.55 / 46.47 ±2.24 / 50.49 ms │ 43.42 / 46.24 ±1.45 / 47.49 ms │     no change │
│ QQuery 8  │ 42.90 / 43.63 ±0.61 / 44.68 ms │ 42.76 / 43.21 ±0.34 / 43.76 ms │     no change │
│ QQuery 9  │ 49.28 / 50.91 ±1.34 / 52.80 ms │ 49.62 / 50.60 ±0.65 / 51.42 ms │     no change │
│ QQuery 10 │ 42.87 / 43.93 ±0.93 / 45.07 ms │ 42.54 / 43.26 ±0.73 / 44.41 ms │     no change │
│ QQuery 11 │ 13.40 / 14.29 ±0.75 / 15.30 ms │ 13.41 / 13.55 ±0.15 / 13.83 ms │ +1.05x faster │
│ QQuery 12 │ 24.17 / 24.80 ±0.60 / 25.82 ms │ 23.65 / 24.49 ±0.56 / 25.23 ms │     no change │
│ QQuery 13 │ 33.53 / 35.00 ±1.27 / 36.79 ms │ 32.48 / 33.73 ±1.26 / 35.97 ms │     no change │
│ QQuery 14 │ 23.94 / 24.16 ±0.14 / 24.35 ms │ 23.79 / 24.33 ±0.71 / 25.72 ms │     no change │
│ QQuery 15 │ 31.60 / 31.87 ±0.18 / 32.05 ms │ 31.18 / 31.55 ±0.42 / 32.34 ms │     no change │
│ QQuery 16 │ 14.08 / 14.28 ±0.13 / 14.41 ms │ 14.07 / 14.27 ±0.14 / 14.43 ms │     no change │
│ QQuery 17 │ 75.50 / 76.55 ±1.17 / 78.41 ms │ 74.48 / 75.73 ±1.18 / 77.76 ms │     no change │
│ QQuery 18 │ 59.28 / 60.44 ±1.21 / 62.74 ms │ 59.93 / 60.96 ±0.69 / 61.90 ms │     no change │
│ QQuery 19 │ 33.43 / 33.68 ±0.31 / 34.26 ms │ 32.73 / 33.48 ±1.10 / 35.66 ms │     no change │
│ QQuery 20 │ 32.61 / 32.84 ±0.16 / 33.10 ms │ 32.09 / 32.50 ±0.24 / 32.81 ms │     no change │
│ QQuery 21 │ 56.07 / 57.03 ±1.01 / 58.84 ms │ 55.09 / 56.93 ±1.28 / 59.11 ms │     no change │
│ QQuery 22 │ 14.11 / 14.21 ±0.11 / 14.39 ms │ 14.16 / 14.32 ±0.16 / 14.54 ms │     no change │
└───────────┴────────────────────────────────┴────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┓
┃ Benchmark Summary                    ┃          ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 771.88ms │
│ Total Time (alamb_update_arrow_59)   │ 765.58ms │
│ Average Time (HEAD)                  │  35.09ms │
│ Average Time (alamb_update_arrow_59) │  34.80ms │
│ Queries Faster                       │        1 │
│ Queries Slower                       │        0 │
│ Queries with No Change               │       21 │
│ Queries with Failure                 │        0 │
└──────────────────────────────────────┴──────────┘

Resource Usage

tpch — base (merge-base)

Metric Value
Wall time 5.0s
Peak memory 5.7 GiB
Avg memory 5.0 GiB
CPU user 30.0s
CPU sys 2.4s
Peak spill 0 B

tpch — branch

Metric Value
Wall time 5.0s
Peak memory 5.7 GiB
Avg memory 5.0 GiB
CPU user 30.0s
CPU sys 2.2s
Peak spill 0 B

File an issue against this benchmark runner

@adriangbot
Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

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

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

Comparing HEAD and alamb_update_arrow_59
--------------------
Benchmark tpcds_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃                alamb_update_arrow_59 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1  │           5.88 / 6.68 ±0.93 / 8.30 ms │          5.99 / 6.48 ±0.85 / 8.17 ms │     no change │
│ QQuery 2  │        80.93 / 81.63 ±1.05 / 83.71 ms │       82.33 / 82.67 ±0.21 / 82.96 ms │     no change │
│ QQuery 3  │        29.02 / 29.21 ±0.17 / 29.51 ms │       28.61 / 29.02 ±0.24 / 29.25 ms │     no change │
│ QQuery 4  │     497.83 / 500.90 ±2.50 / 504.38 ms │    488.01 / 490.57 ±1.97 / 493.22 ms │     no change │
│ QQuery 5  │        51.91 / 52.12 ±0.22 / 52.46 ms │       51.57 / 52.14 ±0.51 / 52.87 ms │     no change │
│ QQuery 6  │        36.69 / 36.90 ±0.12 / 37.04 ms │       36.21 / 36.54 ±0.34 / 37.16 ms │     no change │
│ QQuery 7  │       95.08 / 97.40 ±2.71 / 102.70 ms │       94.13 / 94.87 ±0.79 / 96.41 ms │     no change │
│ QQuery 8  │        36.90 / 37.47 ±0.62 / 38.51 ms │       36.69 / 37.85 ±1.56 / 40.92 ms │     no change │
│ QQuery 9  │        53.89 / 54.65 ±0.63 / 55.81 ms │       54.09 / 56.28 ±2.34 / 59.96 ms │     no change │
│ QQuery 10 │        68.83 / 69.27 ±0.27 / 69.68 ms │       68.84 / 69.03 ±0.15 / 69.26 ms │     no change │
│ QQuery 11 │     301.64 / 306.29 ±2.95 / 309.95 ms │    301.98 / 305.84 ±2.37 / 308.28 ms │     no change │
│ QQuery 12 │        29.00 / 29.18 ±0.14 / 29.39 ms │       28.84 / 29.13 ±0.33 / 29.77 ms │     no change │
│ QQuery 13 │     119.73 / 122.40 ±4.16 / 130.69 ms │    119.25 / 120.02 ±0.55 / 120.89 ms │     no change │
│ QQuery 14 │     413.14 / 416.78 ±3.00 / 420.76 ms │    412.86 / 418.78 ±3.04 / 421.02 ms │     no change │
│ QQuery 15 │        58.86 / 60.05 ±0.73 / 61.06 ms │       59.43 / 60.10 ±0.41 / 60.59 ms │     no change │
│ QQuery 16 │           6.92 / 7.04 ±0.22 / 7.49 ms │          6.91 / 7.08 ±0.18 / 7.41 ms │     no change │
│ QQuery 17 │        81.62 / 82.81 ±1.79 / 86.37 ms │       80.14 / 81.65 ±1.62 / 84.76 ms │     no change │
│ QQuery 18 │     124.59 / 127.11 ±2.30 / 130.94 ms │    124.50 / 126.38 ±2.37 / 131.03 ms │     no change │
│ QQuery 19 │        41.85 / 42.09 ±0.12 / 42.16 ms │       41.84 / 42.03 ±0.23 / 42.36 ms │     no change │
│ QQuery 20 │        35.57 / 35.88 ±0.47 / 36.80 ms │       35.67 / 37.69 ±2.45 / 42.49 ms │  1.05x slower │
│ QQuery 21 │        16.95 / 17.98 ±0.84 / 19.50 ms │       17.04 / 17.36 ±0.24 / 17.64 ms │     no change │
│ QQuery 22 │        62.37 / 63.44 ±0.82 / 64.79 ms │       62.33 / 62.52 ±0.23 / 62.97 ms │     no change │
│ QQuery 23 │     346.25 / 351.88 ±6.50 / 363.60 ms │    342.05 / 347.55 ±4.25 / 355.09 ms │     no change │
│ QQuery 24 │     226.09 / 228.58 ±2.16 / 232.21 ms │    222.70 / 226.40 ±4.36 / 234.53 ms │     no change │
│ QQuery 25 │     110.67 / 112.11 ±0.92 / 113.54 ms │    110.95 / 111.78 ±0.98 / 113.65 ms │     no change │
│ QQuery 26 │        58.49 / 59.25 ±0.72 / 60.41 ms │       58.69 / 60.59 ±3.23 / 67.03 ms │     no change │
│ QQuery 27 │           6.65 / 6.76 ±0.18 / 7.13 ms │          6.70 / 6.85 ±0.17 / 7.19 ms │     no change │
│ QQuery 28 │        60.80 / 61.51 ±0.58 / 62.48 ms │       60.60 / 61.00 ±0.28 / 61.34 ms │     no change │
│ QQuery 29 │       97.82 / 99.11 ±1.56 / 102.13 ms │      97.13 / 99.97 ±4.02 / 107.94 ms │     no change │
│ QQuery 30 │        32.42 / 34.15 ±2.67 / 39.46 ms │       33.39 / 34.80 ±0.74 / 35.54 ms │     no change │
│ QQuery 31 │     112.31 / 113.22 ±0.60 / 114.04 ms │    111.73 / 112.63 ±0.79 / 113.93 ms │     no change │
│ QQuery 32 │        19.88 / 20.18 ±0.27 / 20.68 ms │       20.33 / 20.64 ±0.26 / 21.10 ms │     no change │
│ QQuery 33 │        38.53 / 39.08 ±0.38 / 39.52 ms │       38.79 / 41.15 ±3.13 / 47.20 ms │  1.05x slower │
│ QQuery 34 │         9.36 / 10.80 ±2.42 / 15.62 ms │       10.00 / 10.63 ±0.70 / 11.55 ms │     no change │
│ QQuery 35 │        77.75 / 78.32 ±0.47 / 78.93 ms │       77.45 / 78.16 ±0.70 / 79.48 ms │     no change │
│ QQuery 36 │           5.91 / 6.02 ±0.18 / 6.37 ms │          6.09 / 6.19 ±0.13 / 6.43 ms │     no change │
│ QQuery 37 │           6.86 / 7.06 ±0.16 / 7.31 ms │          6.88 / 7.05 ±0.10 / 7.14 ms │     no change │
│ QQuery 38 │        62.69 / 63.34 ±0.43 / 63.85 ms │       62.15 / 63.01 ±0.63 / 63.87 ms │     no change │
│ QQuery 39 │     449.53 / 456.55 ±5.07 / 464.00 ms │    451.18 / 460.55 ±8.44 / 472.14 ms │     no change │
│ QQuery 40 │        23.21 / 23.45 ±0.25 / 23.82 ms │       23.17 / 23.65 ±0.32 / 24.06 ms │     no change │
│ QQuery 41 │        11.24 / 11.40 ±0.18 / 11.75 ms │       11.31 / 11.44 ±0.17 / 11.78 ms │     no change │
│ QQuery 42 │        23.69 / 24.01 ±0.22 / 24.36 ms │       23.65 / 23.87 ±0.27 / 24.36 ms │     no change │
│ QQuery 43 │           4.94 / 5.02 ±0.12 / 5.26 ms │          4.85 / 4.99 ±0.17 / 5.32 ms │     no change │
│ QQuery 44 │        10.69 / 10.79 ±0.16 / 11.11 ms │       10.74 / 10.84 ±0.08 / 10.94 ms │     no change │
│ QQuery 45 │        38.38 / 39.18 ±0.79 / 40.47 ms │       37.83 / 38.43 ±0.40 / 39.01 ms │     no change │
│ QQuery 46 │        11.87 / 12.23 ±0.40 / 12.99 ms │       11.54 / 11.67 ±0.12 / 11.90 ms │     no change │
│ QQuery 47 │     231.97 / 235.93 ±3.48 / 241.25 ms │    226.03 / 233.54 ±6.26 / 244.43 ms │     no change │
│ QQuery 48 │       97.01 / 99.58 ±2.78 / 104.72 ms │     98.14 / 100.01 ±1.50 / 102.40 ms │     no change │
│ QQuery 49 │        77.47 / 78.61 ±1.27 / 80.98 ms │       77.25 / 78.51 ±0.92 / 79.86 ms │     no change │
│ QQuery 50 │        59.63 / 62.81 ±4.57 / 71.80 ms │       59.38 / 60.20 ±0.67 / 61.38 ms │     no change │
│ QQuery 51 │        91.67 / 94.92 ±2.04 / 97.26 ms │       91.59 / 94.42 ±2.32 / 98.49 ms │     no change │
│ QQuery 52 │        23.92 / 24.18 ±0.24 / 24.49 ms │       23.60 / 24.09 ±0.42 / 24.77 ms │     no change │
│ QQuery 53 │        29.29 / 29.68 ±0.49 / 30.64 ms │       29.35 / 29.59 ±0.18 / 29.90 ms │     no change │
│ QQuery 54 │        55.48 / 59.58 ±4.83 / 67.49 ms │       55.21 / 58.10 ±4.50 / 67.06 ms │     no change │
│ QQuery 55 │        23.90 / 24.35 ±0.29 / 24.69 ms │       23.51 / 23.64 ±0.15 / 23.90 ms │     no change │
│ QQuery 56 │        39.34 / 39.76 ±0.42 / 40.58 ms │       40.12 / 40.60 ±0.40 / 41.10 ms │     no change │
│ QQuery 57 │     176.05 / 178.15 ±2.23 / 182.35 ms │    177.54 / 180.95 ±4.08 / 188.78 ms │     no change │
│ QQuery 58 │     116.20 / 117.60 ±1.08 / 118.81 ms │    116.80 / 117.37 ±0.70 / 118.73 ms │     no change │
│ QQuery 59 │     116.94 / 119.68 ±3.07 / 125.65 ms │    118.60 / 120.04 ±1.96 / 123.76 ms │     no change │
│ QQuery 60 │        39.22 / 39.98 ±0.89 / 41.57 ms │       39.30 / 40.33 ±1.09 / 42.07 ms │     no change │
│ QQuery 61 │        12.89 / 13.00 ±0.16 / 13.32 ms │       13.10 / 13.24 ±0.13 / 13.48 ms │     no change │
│ QQuery 62 │        45.89 / 46.84 ±0.91 / 48.26 ms │       45.96 / 47.79 ±3.02 / 53.80 ms │     no change │
│ QQuery 63 │        29.90 / 31.82 ±3.18 / 38.14 ms │       29.87 / 30.72 ±0.69 / 31.97 ms │     no change │
│ QQuery 64 │     396.95 / 403.37 ±5.57 / 412.60 ms │    391.82 / 402.48 ±9.57 / 418.10 ms │     no change │
│ QQuery 65 │     147.06 / 149.29 ±1.61 / 152.00 ms │    145.19 / 149.96 ±2.88 / 153.65 ms │     no change │
│ QQuery 66 │        78.94 / 81.89 ±3.53 / 88.68 ms │       79.81 / 83.78 ±6.24 / 96.18 ms │     no change │
│ QQuery 67 │     246.46 / 254.23 ±6.15 / 261.47 ms │    245.79 / 252.30 ±3.81 / 257.59 ms │     no change │
│ QQuery 68 │        11.93 / 12.08 ±0.17 / 12.39 ms │       12.03 / 12.20 ±0.15 / 12.48 ms │     no change │
│ QQuery 69 │        62.93 / 63.49 ±0.35 / 63.90 ms │       62.57 / 62.98 ±0.36 / 63.51 ms │     no change │
│ QQuery 70 │     105.91 / 112.14 ±8.10 / 127.44 ms │    106.05 / 109.96 ±5.10 / 119.89 ms │     no change │
│ QQuery 71 │        35.72 / 36.16 ±0.38 / 36.60 ms │       35.35 / 35.65 ±0.25 / 36.11 ms │     no change │
│ QQuery 72 │ 2059.99 / 2190.99 ±93.81 / 2314.84 ms │ 2100.55 / 2111.87 ±7.25 / 2121.01 ms │     no change │
│ QQuery 73 │          9.28 / 9.64 ±0.32 / 10.14 ms │         9.34 / 9.58 ±0.23 / 10.01 ms │     no change │
│ QQuery 74 │     172.31 / 175.72 ±5.18 / 186.00 ms │    169.64 / 174.53 ±5.04 / 182.48 ms │     no change │
│ QQuery 75 │     147.62 / 152.80 ±7.59 / 167.88 ms │    148.02 / 149.29 ±1.07 / 150.63 ms │     no change │
│ QQuery 76 │        35.36 / 36.26 ±0.60 / 37.10 ms │       35.05 / 38.83 ±4.60 / 46.94 ms │  1.07x slower │
│ QQuery 77 │        61.28 / 61.71 ±0.34 / 62.21 ms │       61.92 / 62.52 ±0.52 / 63.32 ms │     no change │
│ QQuery 78 │     189.44 / 195.20 ±7.55 / 209.97 ms │    188.84 / 193.30 ±5.86 / 204.62 ms │     no change │
│ QQuery 79 │        66.63 / 71.50 ±6.16 / 82.04 ms │       66.71 / 67.59 ±0.95 / 69.44 ms │ +1.06x faster │
│ QQuery 80 │      99.83 / 102.92 ±2.15 / 106.55 ms │    100.21 / 102.34 ±1.94 / 105.88 ms │     no change │
│ QQuery 81 │        25.51 / 25.75 ±0.27 / 26.27 ms │       25.64 / 25.94 ±0.28 / 26.41 ms │     no change │
│ QQuery 82 │        16.36 / 16.53 ±0.17 / 16.78 ms │       16.37 / 16.70 ±0.23 / 16.96 ms │     no change │
│ QQuery 83 │        39.62 / 41.84 ±4.03 / 49.90 ms │       40.03 / 41.29 ±2.33 / 45.95 ms │     no change │
│ QQuery 84 │        34.51 / 36.89 ±3.94 / 44.75 ms │       34.26 / 34.47 ±0.16 / 34.76 ms │ +1.07x faster │
│ QQuery 85 │     108.69 / 109.28 ±0.39 / 109.77 ms │    106.93 / 110.78 ±4.50 / 119.37 ms │     no change │
│ QQuery 86 │        24.78 / 25.38 ±0.46 / 25.82 ms │       24.77 / 25.44 ±0.55 / 26.18 ms │     no change │
│ QQuery 87 │        64.42 / 66.81 ±3.50 / 73.74 ms │       62.58 / 63.41 ±0.49 / 63.87 ms │ +1.05x faster │
│ QQuery 88 │        62.97 / 63.15 ±0.17 / 63.41 ms │       61.98 / 62.82 ±0.89 / 64.40 ms │     no change │
│ QQuery 89 │        35.63 / 36.24 ±0.42 / 36.74 ms │       36.35 / 36.84 ±0.35 / 37.24 ms │     no change │
│ QQuery 90 │        16.81 / 17.12 ±0.23 / 17.40 ms │       16.95 / 17.13 ±0.17 / 17.45 ms │     no change │
│ QQuery 91 │        44.53 / 44.67 ±0.12 / 44.84 ms │       44.69 / 45.11 ±0.24 / 45.41 ms │     no change │
│ QQuery 92 │        29.69 / 32.00 ±3.22 / 38.39 ms │       29.08 / 29.35 ±0.32 / 29.95 ms │ +1.09x faster │
│ QQuery 93 │        50.39 / 51.60 ±0.93 / 53.14 ms │       50.70 / 51.36 ±0.61 / 52.50 ms │     no change │
│ QQuery 94 │        38.97 / 39.49 ±0.54 / 40.46 ms │       38.92 / 41.18 ±3.21 / 47.51 ms │     no change │
│ QQuery 95 │        84.51 / 86.05 ±2.49 / 91.02 ms │       84.24 / 85.29 ±0.95 / 86.65 ms │     no change │
│ QQuery 96 │        24.28 / 24.56 ±0.29 / 25.10 ms │       23.55 / 23.92 ±0.27 / 24.40 ms │     no change │
│ QQuery 97 │        45.88 / 46.55 ±0.46 / 47.20 ms │       45.80 / 46.33 ±0.54 / 47.32 ms │     no change │
│ QQuery 98 │        42.83 / 43.90 ±0.76 / 45.04 ms │       43.73 / 44.94 ±1.42 / 47.00 ms │     no change │
│ QQuery 99 │        69.69 / 69.81 ±0.13 / 70.02 ms │       69.87 / 70.50 ±0.44 / 71.04 ms │     no change │
└───────────┴───────────────────────────────────────┴──────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                    ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 10434.75ms │
│ Total Time (alamb_update_arrow_59)   │ 10322.94ms │
│ Average Time (HEAD)                  │   105.40ms │
│ Average Time (alamb_update_arrow_59) │   104.27ms │
│ Queries Faster                       │          4 │
│ Queries Slower                       │          3 │
│ Queries with No Change               │         92 │
│ Queries with Failure                 │          0 │
└──────────────────────────────────────┴────────────┘

Resource Usage

tpcds — base (merge-base)

Metric Value
Wall time 55.0s
Peak memory 7.0 GiB
Avg memory 6.3 GiB
CPU user 237.6s
CPU sys 6.6s
Peak spill 0 B

tpcds — branch

Metric Value
Wall time 55.0s
Peak memory 7.3 GiB
Avg memory 6.5 GiB
CPU user 233.7s
CPU sys 6.4s
Peak spill 0 B

File an issue against this benchmark runner

@adriangbot
Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

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

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

Comparing HEAD and alamb_update_arrow_59
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃                 alamb_update_arrow_59 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.17 / 3.33 ±4.29 / 11.91 ms │          1.15 / 3.28 ±4.18 / 11.64 ms │     no change │
│ QQuery 1  │        12.20 / 12.52 ±0.18 / 12.72 ms │        12.95 / 13.42 ±0.27 / 13.74 ms │  1.07x slower │
│ QQuery 2  │        35.63 / 35.93 ±0.22 / 36.29 ms │        36.29 / 36.86 ±0.58 / 37.86 ms │     no change │
│ QQuery 3  │        31.20 / 32.28 ±0.81 / 33.22 ms │        30.66 / 31.28 ±0.66 / 32.34 ms │     no change │
│ QQuery 4  │     224.70 / 227.47 ±1.66 / 229.61 ms │     217.35 / 225.11 ±3.94 / 228.34 ms │     no change │
│ QQuery 5  │     270.83 / 272.40 ±2.06 / 276.47 ms │     272.55 / 274.51 ±1.24 / 275.75 ms │     no change │
│ QQuery 6  │           1.19 / 1.34 ±0.21 / 1.75 ms │           1.18 / 1.34 ±0.22 / 1.76 ms │     no change │
│ QQuery 7  │        13.41 / 13.51 ±0.09 / 13.65 ms │        14.54 / 14.68 ±0.13 / 14.91 ms │  1.09x slower │
│ QQuery 8  │     318.57 / 325.26 ±4.54 / 330.60 ms │     321.81 / 330.28 ±7.76 / 344.54 ms │     no change │
│ QQuery 9  │     454.33 / 461.13 ±3.72 / 465.67 ms │     450.53 / 463.44 ±9.15 / 475.65 ms │     no change │
│ QQuery 10 │        69.39 / 69.92 ±0.43 / 70.64 ms │        68.69 / 69.15 ±0.39 / 69.58 ms │     no change │
│ QQuery 11 │        79.27 / 80.76 ±1.20 / 82.23 ms │        79.47 / 82.69 ±3.55 / 89.50 ms │     no change │
│ QQuery 12 │     264.82 / 271.22 ±4.26 / 277.13 ms │     264.87 / 269.92 ±5.20 / 279.77 ms │     no change │
│ QQuery 13 │    364.29 / 380.54 ±15.72 / 406.96 ms │    366.88 / 375.97 ±10.26 / 392.81 ms │     no change │
│ QQuery 14 │     278.89 / 283.32 ±3.54 / 288.71 ms │     282.98 / 294.36 ±9.56 / 307.01 ms │     no change │
│ QQuery 15 │     270.91 / 276.45 ±5.03 / 284.86 ms │    269.20 / 282.10 ±10.87 / 296.69 ms │     no change │
│ QQuery 16 │     610.10 / 617.50 ±6.25 / 627.65 ms │     612.36 / 622.82 ±5.97 / 629.27 ms │     no change │
│ QQuery 17 │    609.52 / 622.40 ±12.24 / 642.07 ms │     626.35 / 631.41 ±4.18 / 638.46 ms │     no change │
│ QQuery 18 │ 1242.77 / 1260.83 ±18.83 / 1291.91 ms │ 1268.95 / 1293.87 ±15.83 / 1312.89 ms │     no change │
│ QQuery 19 │        27.10 / 30.79 ±6.99 / 44.76 ms │       27.94 / 35.93 ±14.94 / 65.79 ms │  1.17x slower │
│ QQuery 20 │     515.70 / 522.33 ±7.56 / 536.93 ms │     517.58 / 526.77 ±7.24 / 536.70 ms │     no change │
│ QQuery 21 │     515.27 / 525.45 ±7.15 / 536.83 ms │     522.59 / 524.87 ±2.30 / 528.14 ms │     no change │
│ QQuery 22 │  983.26 / 1000.05 ±13.49 / 1023.60 ms │    985.11 / 998.23 ±7.18 / 1007.09 ms │     no change │
│ QQuery 23 │ 3182.90 / 3212.98 ±16.93 / 3232.64 ms │ 3188.63 / 3209.90 ±18.33 / 3243.25 ms │     no change │
│ QQuery 24 │        41.69 / 45.13 ±5.25 / 55.58 ms │        42.00 / 44.61 ±4.18 / 52.94 ms │     no change │
│ QQuery 25 │     110.82 / 112.87 ±2.33 / 117.26 ms │     111.76 / 116.35 ±6.62 / 129.43 ms │     no change │
│ QQuery 26 │        42.03 / 44.87 ±3.71 / 52.09 ms │        42.54 / 44.87 ±2.76 / 50.12 ms │     no change │
│ QQuery 27 │     672.44 / 680.00 ±5.82 / 687.24 ms │     674.85 / 682.09 ±4.74 / 687.76 ms │     no change │
│ QQuery 28 │ 3039.25 / 3066.76 ±28.00 / 3117.42 ms │ 3038.91 / 3056.75 ±13.24 / 3074.09 ms │     no change │
│ QQuery 29 │        39.95 / 42.91 ±5.36 / 53.63 ms │        40.13 / 44.90 ±8.28 / 61.45 ms │     no change │
│ QQuery 30 │     300.04 / 302.76 ±2.77 / 307.30 ms │     298.24 / 307.88 ±9.36 / 325.15 ms │     no change │
│ QQuery 31 │    282.02 / 298.98 ±16.50 / 327.56 ms │    279.43 / 294.49 ±12.73 / 316.34 ms │     no change │
│ QQuery 32 │    914.06 / 939.79 ±17.56 / 963.74 ms │   958.27 / 992.13 ±26.59 / 1034.02 ms │  1.06x slower │
│ QQuery 33 │ 1432.57 / 1458.93 ±14.01 / 1473.70 ms │ 1443.62 / 1455.31 ±10.05 / 1469.98 ms │     no change │
│ QQuery 34 │ 1466.50 / 1483.23 ±11.02 / 1495.37 ms │ 1468.92 / 1525.23 ±65.32 / 1652.47 ms │     no change │
│ QQuery 35 │    280.39 / 295.13 ±17.47 / 328.84 ms │    282.81 / 299.96 ±27.59 / 354.86 ms │     no change │
│ QQuery 36 │        65.78 / 73.89 ±6.19 / 84.51 ms │        65.89 / 69.53 ±2.04 / 71.26 ms │ +1.06x faster │
│ QQuery 37 │        35.53 / 43.16 ±8.73 / 58.93 ms │        34.87 / 37.92 ±4.65 / 47.06 ms │ +1.14x faster │
│ QQuery 38 │        42.49 / 44.39 ±2.86 / 49.98 ms │        42.20 / 46.56 ±2.92 / 48.98 ms │     no change │
│ QQuery 39 │     138.50 / 148.95 ±7.19 / 159.40 ms │     136.29 / 151.02 ±9.09 / 161.05 ms │     no change │
│ QQuery 40 │        13.51 / 14.09 ±0.43 / 14.66 ms │        15.08 / 16.96 ±2.06 / 20.63 ms │  1.20x slower │
│ QQuery 41 │        13.44 / 15.09 ±3.11 / 21.30 ms │        13.87 / 17.46 ±4.54 / 25.43 ms │  1.16x slower │
│ QQuery 42 │        12.63 / 13.13 ±0.47 / 13.97 ms │        12.85 / 14.85 ±3.68 / 22.21 ms │  1.13x slower │
└───────────┴───────────────────────────────────────┴───────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                    ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 19663.76ms │
│ Total Time (alamb_update_arrow_59)   │ 19831.08ms │
│ Average Time (HEAD)                  │   457.30ms │
│ Average Time (alamb_update_arrow_59) │   461.19ms │
│ Queries Faster                       │          2 │
│ Queries Slower                       │          7 │
│ Queries with No Change               │         34 │
│ Queries with Failure                 │          0 │
└──────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric Value
Wall time 100.0s
Peak memory 30.4 GiB
Avg memory 23.2 GiB
CPU user 1014.0s
CPU sys 72.8s
Peak spill 0 B

clickbench_partitioned — branch

Metric Value
Wall time 100.0s
Peak memory 30.1 GiB
Avg memory 23.2 GiB
CPU user 1016.7s
CPU sys 75.3s
Peak spill 0 B

File an issue against this benchmark runner

@alamb
Copy link
Copy Markdown
Contributor Author

alamb commented Jun 4, 2026

run benchmark clickbench_partitioned

@adriangbot
Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4625765533-446-ksw9c 6.12.68+ #1 SMP Wed Apr 1 02:23:28 UTC 2026 aarch64 GNU/Linux

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

Comparing alamb/update_arrow_59 (4d274ef) to 18e7c8e (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot
Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

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

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

Comparing HEAD and alamb_update_arrow_59
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃                 alamb_update_arrow_59 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.17 / 3.36 ±4.27 / 11.90 ms │          1.14 / 3.35 ±4.29 / 11.92 ms │     no change │
│ QQuery 1  │        12.38 / 12.76 ±0.19 / 12.90 ms │        12.81 / 13.20 ±0.23 / 13.49 ms │     no change │
│ QQuery 2  │        36.12 / 37.87 ±1.89 / 40.57 ms │        35.75 / 35.91 ±0.18 / 36.25 ms │ +1.05x faster │
│ QQuery 3  │        30.38 / 31.01 ±0.69 / 32.28 ms │        30.47 / 30.60 ±0.14 / 30.84 ms │     no change │
│ QQuery 4  │     225.85 / 227.88 ±1.44 / 230.11 ms │     224.73 / 228.28 ±2.58 / 232.66 ms │     no change │
│ QQuery 5  │     272.82 / 274.76 ±1.74 / 277.47 ms │     272.28 / 275.00 ±2.56 / 279.60 ms │     no change │
│ QQuery 6  │           1.20 / 1.35 ±0.23 / 1.79 ms │           1.16 / 1.31 ±0.22 / 1.75 ms │     no change │
│ QQuery 7  │        13.70 / 13.91 ±0.21 / 14.31 ms │        14.44 / 14.73 ±0.20 / 14.97 ms │  1.06x slower │
│ QQuery 8  │     327.18 / 332.21 ±3.35 / 336.90 ms │     328.94 / 332.99 ±6.52 / 345.98 ms │     no change │
│ QQuery 9  │     456.86 / 461.90 ±4.91 / 471.13 ms │     465.95 / 474.86 ±6.98 / 487.48 ms │     no change │
│ QQuery 10 │        69.53 / 70.72 ±0.99 / 72.47 ms │        69.26 / 70.08 ±0.75 / 71.13 ms │     no change │
│ QQuery 11 │        80.95 / 82.04 ±0.99 / 83.47 ms │        80.97 / 81.71 ±0.74 / 83.08 ms │     no change │
│ QQuery 12 │     268.29 / 273.58 ±4.34 / 280.87 ms │     274.03 / 275.82 ±1.52 / 278.17 ms │     no change │
│ QQuery 13 │     376.84 / 386.12 ±9.58 / 402.21 ms │    378.09 / 401.46 ±11.93 / 410.56 ms │     no change │
│ QQuery 14 │     285.52 / 291.50 ±7.85 / 306.90 ms │     287.03 / 290.67 ±4.51 / 299.38 ms │     no change │
│ QQuery 15 │    274.46 / 287.14 ±10.43 / 306.21 ms │     277.51 / 285.97 ±6.43 / 296.97 ms │     no change │
│ QQuery 16 │    618.48 / 634.16 ±13.18 / 652.07 ms │     635.11 / 645.56 ±7.71 / 653.73 ms │     no change │
│ QQuery 17 │    620.90 / 634.28 ±10.43 / 652.28 ms │     634.50 / 646.91 ±9.47 / 658.04 ms │     no change │
│ QQuery 18 │ 1283.58 / 1300.88 ±14.10 / 1326.71 ms │ 1303.73 / 1334.81 ±21.06 / 1362.68 ms │     no change │
│ QQuery 19 │        27.39 / 27.53 ±0.12 / 27.74 ms │        28.74 / 29.07 ±0.20 / 29.36 ms │  1.06x slower │
│ QQuery 20 │    518.46 / 528.53 ±10.38 / 546.37 ms │     515.93 / 525.65 ±8.94 / 541.50 ms │     no change │
│ QQuery 21 │     519.36 / 525.88 ±3.65 / 530.43 ms │     511.97 / 516.82 ±3.14 / 520.64 ms │     no change │
│ QQuery 22 │  985.75 / 1007.97 ±18.38 / 1040.97 ms │   990.10 / 1004.17 ±9.31 / 1016.37 ms │     no change │
│ QQuery 23 │ 3196.09 / 3212.79 ±13.46 / 3234.44 ms │ 3196.73 / 3223.82 ±22.43 / 3253.43 ms │     no change │
│ QQuery 24 │       41.67 / 47.60 ±10.56 / 68.70 ms │       40.97 / 49.19 ±10.66 / 69.05 ms │     no change │
│ QQuery 25 │     111.62 / 115.63 ±5.24 / 125.72 ms │     110.88 / 112.92 ±1.66 / 115.20 ms │     no change │
│ QQuery 26 │        41.37 / 42.99 ±1.62 / 46.06 ms │        41.35 / 44.62 ±3.65 / 49.97 ms │     no change │
│ QQuery 27 │     670.12 / 678.98 ±8.07 / 693.88 ms │     668.97 / 676.95 ±7.43 / 690.84 ms │     no change │
│ QQuery 28 │ 3057.93 / 3076.61 ±20.74 / 3114.12 ms │ 3034.18 / 3046.92 ±10.39 / 3058.39 ms │     no change │
│ QQuery 29 │        40.30 / 40.62 ±0.32 / 41.11 ms │       40.74 / 54.04 ±17.47 / 85.30 ms │  1.33x slower │
│ QQuery 30 │    305.25 / 313.83 ±11.34 / 334.17 ms │    306.62 / 325.19 ±14.14 / 350.45 ms │     no change │
│ QQuery 31 │     283.28 / 293.84 ±9.29 / 307.63 ms │    291.25 / 312.50 ±16.98 / 337.90 ms │  1.06x slower │
│ QQuery 32 │    942.94 / 968.46 ±17.48 / 988.84 ms │  980.14 / 1055.44 ±61.19 / 1161.05 ms │  1.09x slower │
│ QQuery 33 │ 1483.71 / 1501.14 ±17.36 / 1533.18 ms │ 1465.39 / 1499.71 ±32.05 / 1550.02 ms │     no change │
│ QQuery 34 │ 1515.65 / 1568.93 ±34.63 / 1622.90 ms │ 1467.83 / 1512.18 ±36.40 / 1557.70 ms │     no change │
│ QQuery 35 │    284.24 / 298.22 ±13.77 / 324.14 ms │    282.78 / 329.87 ±85.20 / 500.12 ms │  1.11x slower │
│ QQuery 36 │        67.92 / 73.80 ±5.71 / 84.60 ms │        66.27 / 69.09 ±2.26 / 72.27 ms │ +1.07x faster │
│ QQuery 37 │        35.61 / 39.98 ±5.12 / 46.40 ms │        35.47 / 42.83 ±8.89 / 58.38 ms │  1.07x slower │
│ QQuery 38 │        40.35 / 43.20 ±1.50 / 44.65 ms │        40.42 / 43.66 ±2.94 / 47.80 ms │     no change │
│ QQuery 39 │     150.31 / 155.54 ±4.27 / 161.49 ms │     146.16 / 154.02 ±8.19 / 165.87 ms │     no change │
│ QQuery 40 │        14.04 / 14.67 ±0.78 / 15.93 ms │        14.50 / 16.81 ±4.20 / 25.19 ms │  1.15x slower │
│ QQuery 41 │        13.58 / 14.67 ±1.52 / 17.66 ms │        13.84 / 15.70 ±2.35 / 20.33 ms │  1.07x slower │
│ QQuery 42 │        12.82 / 16.13 ±5.85 / 27.81 ms │        13.24 / 13.51 ±0.19 / 13.73 ms │ +1.19x faster │
└───────────┴───────────────────────────────────────┴───────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                    ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 19964.98ms │
│ Total Time (alamb_update_arrow_59)   │ 20117.91ms │
│ Average Time (HEAD)                  │   464.30ms │
│ Average Time (alamb_update_arrow_59) │   467.86ms │
│ Queries Faster                       │          3 │
│ Queries Slower                       │          9 │
│ Queries with No Change               │         31 │
│ Queries with Failure                 │          0 │
└──────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric Value
Wall time 105.0s
Peak memory 29.1 GiB
Avg memory 22.7 GiB
CPU user 1023.6s
CPU sys 75.9s
Peak spill 0 B

clickbench_partitioned — branch

Metric Value
Wall time 105.0s
Peak memory 30.6 GiB
Avg memory 22.9 GiB
CPU user 1026.5s
CPU sys 78.0s
Peak spill 0 B

File an issue against this benchmark runner

@alamb
Copy link
Copy Markdown
Contributor Author

alamb commented Jun 4, 2026

Performance looks about the same

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

Labels

auto detected api change Auto detected API change common Related to common crate core Core DataFusion crate datasource Changes to the datasource crate physical-expr Changes to the physical-expr crates physical-plan Changes to the physical-plan crate spark

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants