search

voltrondata-labs / benchmarks

Language-independent Continuous Benchmarking (CB) for Apache Arrow
MIT License
10 stars 11 forks source link

Only run TPC-H scale_factor = 10 when memory >= 64 GB #141

Closed alistaire47 closed 1 year ago

alistaire47 commented 1 year ago

TPC-H query 21 at scale factor 10 has been regularly failing on machines with less than 64 GB of memory, e.g. https://buildkite.com/apache-arrow/arrow-bci-benchmark-on-arm64-t4g-linux-compute/builds/2829#0188b088-42b8-4218-ae4a-93dd0058ce8c As a solution, remove scale_factor=10 permutations in get_valid_cases() when there is insufficient memory.

https://github.com/voltrondata-labs/benchmarks/blob/606f4fc986a320dc5c7c5ebefab2540fae578edb/benchmarks/tpch_benchmark.py#L6-L12

jgehrcke commented 1 year ago

TPC-H query 21 at scale factor 10 has been regularly failing on machines with less than 64 GB of memory, e.g. https://buildkite.com/apache-arrow/arrow-bci-benchmark-on-arm64-t4g-linux-compute/builds/2829#0188b088-42b8-4218-ae4a-93dd0058ce8c

The issue tracking that is https://github.com/voltrondata-labs/arrow-benchmarks-ci/issues/64 right?

alistaire47 commented 1 year ago

Yep, thanks for the link! This is the repo that will need the PR though.