Add Pivot

[giladkl]

Hi! Thanks for maintaining ClickBench!

Adds Pivot, a Rust, PostgreSQL-compatible query engine, in two variants: pivot-parquet (single file) and pivot-parquet-partitioned (100 files). Both install via the official installer and query the Parquet in place through psql, with default settings.

When running the benchmark, would it be possible to run it on all machines (machine:all)? If not all, c8g.metal-48xl and c8g.4xlarge are the ones we're mostly looking on.

Thanks a lot!

[CLAassistant]

All committers have signed the CLA.

[github-actions]

Results for pivot-parquet are ready for: c6a.4xlarge.
Results for pivot-parquet-partitioned are ready for: c6a.4xlarge.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet-partitioned/results/20260929/c6a.4xlarge.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet/results/20260929/c6a.4xlarge.json.
Tick "Allow edits by maintainers" on the pull request to let the automation commit the results itself.

Logs:

• pivot-parquet-partitioned on c6a.4xlarge: benchmark log, cloud-init log
• pivot-parquet on c6a.4xlarge: benchmark log, cloud-init log

[giladkl]

Hi @alexey-milovidov - added the results from the bot in a new commit.

Could you also run it with machine:all? We’ve put substantial work into NUMA-aware execution and high parallelism, which isn’t fully reflected on the smaller instance.

[github-actions]

Results for pivot-parquet are ready for: c6a.2xlarge, c6a.4xlarge, c6a.metal, c6a.xlarge, c7a.metal-48xl, c8g.4xlarge, c8g.metal-48xl.
Results for pivot-parquet-partitioned are ready for: c6a.2xlarge, c6a.4xlarge, c6a.metal, c6a.xlarge, c7a.metal-48xl, c8g.4xlarge, c8g.metal-48xl.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet-partitioned/results/20261001/c8g.4xlarge.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet-partitioned/results/20261001/c6a.4xlarge.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet/results/20261001/c8g.4xlarge.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet-partitioned/results/20261001/c8g.metal-48xl.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet-partitioned/results/20261001/c6a.2xlarge.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet-partitioned/results/20261001/c7a.metal-48xl.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet/results/20261001/c6a.4xlarge.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet-partitioned/results/20261001/c6a.xlarge.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet/results/20261001/c6a.2xlarge.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet/results/20261001/c6a.xlarge.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet/results/20261001/c8g.metal-48xl.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet-partitioned/results/20261001/c6a.metal.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet/results/20261001/c7a.metal-48xl.json.
This pull request is from a fork, so the automation cannot push to it; save this result as pivot-parquet/results/20261001/c6a.metal.json.
Tick "Allow edits by maintainers" on the pull request to let the automation commit the results itself.
The run of pivot-parquet on c6a.large did not produce results.
The run of pivot-parquet on t3a.small did not produce results.
The run of pivot-parquet-partitioned on c6a.large did not produce results.
The run of pivot-parquet-partitioned on t3a.small did not produce results.

Logs:

• pivot-parquet on c6a.large: benchmark log, cloud-init log
• pivot-parquet-partitioned on c6a.large: benchmark log, cloud-init log
• pivot-parquet-partitioned on c8g.4xlarge: benchmark log, cloud-init log
• pivot-parquet on t3a.small: benchmark log, cloud-init log
• pivot-parquet-partitioned on t3a.small: benchmark log, cloud-init log
• pivot-parquet-partitioned on c6a.4xlarge: benchmark log, cloud-init log
• pivot-parquet on c8g.4xlarge: benchmark log, cloud-init log
• pivot-parquet-partitioned on c8g.metal-48xl: benchmark log, cloud-init log
• pivot-parquet-partitioned on c6a.2xlarge: benchmark log, cloud-init log
• pivot-parquet-partitioned on c7a.metal-48xl: benchmark log, cloud-init log
• pivot-parquet on c6a.4xlarge: benchmark log, cloud-init log
• pivot-parquet-partitioned on c6a.xlarge: benchmark log, cloud-init log
• pivot-parquet on c6a.2xlarge: benchmark log, cloud-init log
• pivot-parquet on c6a.xlarge: benchmark log, cloud-init log
• pivot-parquet on c8g.metal-48xl: benchmark log, cloud-init log
• pivot-parquet-partitioned on c6a.metal: benchmark log, cloud-init log
• pivot-parquet on c7a.metal-48xl: benchmark log, cloud-init log
• pivot-parquet on c6a.metal: benchmark log, cloud-init log

[giladkl]

@alexey-milovidov Added a new commit with the full results - thanks! :)

Looks good to merge, at least from our side.