alamb commented on code in PR #15367:
URL: https://github.com/apache/datafusion/pull/15367#discussion_r2012933341
##########
datafusion/core/benches/distinct_query_sql.rs:
##########
@@ -144,59 +141,50 @@ pub async fn create_context_sampled_data(
}
fn criterion_benchmark_limited_distinct_sampled(c: &mut Criterion) {
- let rt = Runtime::new().unwrap();
-
let limit = 10;
let partitions = 100;
let samples = 100_000;
let sql =
format!("select DISTINCT trace_id from traces group by trace_id limit
{limit};");
-
- let distinct_trace_id_100_partitions_100_000_samples_limit_100 =
rt.block_on(async {
- create_context_sampled_data(sql.as_str(), partitions, samples)
- .await
- .unwrap()
- });
-
c.bench_function(
format!("distinct query with {} partitions and {} samples per
partition with limit {}", partitions, samples, limit).as_str(),
- |b| b.iter(||
run(distinct_trace_id_100_partitions_100_000_samples_limit_100.0.clone(),
-
distinct_trace_id_100_partitions_100_000_samples_limit_100.1.clone())),
+ |b| b.iter(|| {
+ let rt = Runtime::new().unwrap();
Review Comment:
I think this means that the benchmark will include the time to create each
tokio runtime (with a bunch of threads, etc)
To avoid this I think you can create the runtime once, and then use it for
each tieration:
```rist
let rt = Runtime::new().unwrap();
c.bench_function(
format!("distinct query with {} partitions and {} samples per
partition with limit {}", partitions, samples, limit).as_str(),
|b| b.iter(|| {
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
