metesynnada commented on code in PR #4694: URL: https://github.com/apache/arrow-datafusion/pull/4694#discussion_r1058119291
########## datafusion/core/src/physical_optimizer/pipeline_checker.rs: ########## @@ -0,0 +1,1173 @@ +// 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. + +//! PipelineChecker rule is ensures that a given plan can accommodate its +//! infinite sources, if there are any. +//! +use crate::error::Result; +use crate::physical_optimizer::join_selection::swap_hash_join; +use crate::physical_optimizer::PhysicalOptimizerRule; +use crate::physical_plan::joins::{HashJoinExec, PartitionMode}; +use crate::physical_plan::rewrite::TreeNodeRewritable; +use crate::physical_plan::{with_new_children_if_necessary, ExecutionPlan}; +use crate::prelude::SessionConfig; +use datafusion_common::DataFusionError; +use datafusion_expr::logical_plan::JoinType; +use std::sync::Arc; + +/// The PipelineChecker rule ensures that the given plan can accommodate +/// its infinite sources, if there are any. It will reject any plan with +/// pipeline-breaking operators with an diagnostic error message. +#[derive(Default)] +pub struct PipelineChecker {} + +impl PipelineChecker { + #[allow(missing_docs)] + pub fn new() -> Self { + Self {} + } +} +type PipelineCheckerSubrule = + dyn Fn(&PipelineStatePropagator) -> Option<Result<PipelineStatePropagator>>; +impl PhysicalOptimizerRule for PipelineChecker { + fn optimize( + &self, + plan: Arc<dyn ExecutionPlan>, + _config: &SessionConfig, + ) -> Result<Arc<dyn ExecutionPlan>> { + let pipeline = PipelineStatePropagator::new(plan); + let physical_optimizer_subrules: Vec<Box<PipelineCheckerSubrule>> = + vec![Box::new(hash_join_swap_subrule)]; + let state = pipeline.transform_up(&|p| { Review Comment: Yes, we are planning to expand this type of subrules. Separating the `PipelineChecker` into multiple `PhysicalOptimizerRule` will add redundant plan traversals (and possibly a fixed point iteration), we plan to make the necessary changes for all possible executor changes while we are traversing. -- 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]
