avantgardnerio commented on code in PR #7192: URL: https://github.com/apache/arrow-datafusion/pull/7192#discussion_r1298650520
########## datafusion/core/benches/topk_aggregate.rs: ########## @@ -0,0 +1,239 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you under the Apache License, Version 2.0 (the +// "License"); you may not use this file except in compliance +// with the License. You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, +// software distributed under the License is distributed on an +// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +// KIND, either express or implied. See the License for the +// specific language governing permissions and limitations +// under the License. + +use arrow::util::pretty::pretty_format_batches; +use arrow::{datatypes::Schema, record_batch::RecordBatch}; +use arrow_array::builder::{Int64Builder, StringBuilder}; +use arrow_schema::{DataType, Field, SchemaRef}; +use criterion::{criterion_group, criterion_main, Criterion}; +use datafusion::physical_plan::{collect, displayable, ExecutionPlan}; +use datafusion::prelude::SessionContext; +use datafusion::{datasource::MemTable, error::Result}; +use datafusion_common::DataFusionError; +use datafusion_execution::config::SessionConfig; +use datafusion_execution::TaskContext; +use rand_distr::Distribution; +use rand_distr::{Normal, Pareto}; +use std::sync::Arc; +use tokio::runtime::Runtime; + +async fn create_context( + limit: usize, + partition_cnt: i32, + sample_cnt: i32, + asc: bool, + use_topk: bool, +) -> Result<(Arc<dyn ExecutionPlan>, Arc<TaskContext>)> { + let (schema, parts) = make_data(partition_cnt, sample_cnt, asc).unwrap(); + let mem_table = Arc::new(MemTable::try_new(schema, parts).unwrap()); + + // Create the DataFrame + let mut cfg = SessionConfig::new(); + let opts = cfg.options_mut(); + opts.optimizer.enable_topk_aggregation = use_topk; + let ctx = SessionContext::with_config(cfg); + let _ = ctx.register_table("traces", mem_table)?; + let sql = format!("select trace_id, max(timestamp_ms) from traces group by trace_id order by max(timestamp_ms) desc limit {limit};"); Review Comment: I think this comment was just a misunderstanding about the intended scope of the PR. I've added an "out of scope" section to the PR description to remove any confusion. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
