Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Use 2 partitions in planner tests #17

Merged
merged 3 commits into from
Oct 4, 2024
Merged

Use 2 partitions in planner tests #17

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4aa5435
test with 2 partitions
andygrove Oct 4, 2024
fc594b3
new plans
andygrove Oct 4, 2024
78dc8d6
regenerate with single partition of input data
andygrove Oct 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 0 additions & 20 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,26 +145,6 @@ export TPCH_DATA_PATH=`pwd`/data
cargo test
```

Tests compare plans with expected plans, which unfortunately contain the
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If this is not needed anymore, can we also remove the script ?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It was removed in my previous PR, but I missed this documentation

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ooops, my previous review was not deep enough

path to the parquet tables. The path committed under version control is
the one of a Github Runner, and won't work locally. You can fix it by
running the following command:

```bash
./scripts/replace-expected-plan-paths.sh local-dev
````

When instead you need to regenerate the plans, which you can do by
re-running the planner tests removing all the content of
`testdata/expected-plans`, they will now contain your local paths. You can
fix it before committing the plans running

```bash

./scripts/replace-expected-plan-paths.sh pre-ci

```

## Benchmarking

Create a release build when running benchmarks, then use pip to install the wheel.
Expand Down
6 changes: 3 additions & 3 deletions src/planner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -394,8 +394,8 @@ mod test {

let file = format!("testdata/queries/q{n}.sql");
let sql = fs::read_to_string(&file)?;
let config = SessionConfig::new().with_target_partitions(1);
let ctx = SessionContext::with_config(config);
let config = SessionConfig::new().with_target_partitions(2);
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is the main change

let ctx = SessionContext::new_with_config(config);
let tables = &[
"customer", "lineitem", "nation", "orders", "part", "partsupp", "region", "supplier",
];
Expand Down Expand Up @@ -423,7 +423,7 @@ mod test {
displayable(plan.as_ref()).indent(false)
));

output.push_str("RaySQL Plan\n===========\n\n");
output.push_str("DataFusion Ray Distributed Plan\n===========\n\n");
let graph = make_execution_graph(plan, false)?;
for id in 0..=graph.get_final_query_stage().id {
let query_stage = graph.query_stages.get(&id).unwrap();
Expand Down
43 changes: 29 additions & 14 deletions testdata/expected-plans/q1.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,23 +11,38 @@ Sort: lineitem.l_returnflag ASC NULLS LAST, lineitem.l_linestatus ASC NULLS LAST
DataFusion Physical Plan
========================

SortExec: expr=[l_returnflag@0 ASC NULLS LAST,l_linestatus@1 ASC NULLS LAST], preserve_partitioning=[false]
ProjectionExec: expr=[l_returnflag@0 as l_returnflag, l_linestatus@1 as l_linestatus, sum(lineitem.l_quantity)@2 as sum_qty, sum(lineitem.l_extendedprice)@3 as sum_base_price, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)@4 as sum_disc_price, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax)@5 as sum_charge, avg(lineitem.l_quantity)@6 as avg_qty, avg(lineitem.l_extendedprice)@7 as avg_price, avg(lineitem.l_discount)@8 as avg_disc, count(*)@9 as count_order]
AggregateExec: mode=Single, gby=[l_returnflag@5 as l_returnflag, l_linestatus@6 as l_linestatus], aggr=[sum(lineitem.l_quantity), sum(lineitem.l_extendedprice), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax), avg(lineitem.l_quantity), avg(lineitem.l_extendedprice), avg(lineitem.l_discount), count(*)]
ProjectionExec: expr=[l_extendedprice@1 * (Some(1),20,0 - l_discount@2) as __common_expr_2, l_quantity@0 as l_quantity, l_extendedprice@1 as l_extendedprice, l_discount@2 as l_discount, l_tax@3 as l_tax, l_returnflag@4 as l_returnflag, l_linestatus@5 as l_linestatus]
SortPreservingMergeExec: [l_returnflag@0 ASC NULLS LAST,l_linestatus@1 ASC NULLS LAST]
SortExec: expr=[l_returnflag@0 ASC NULLS LAST,l_linestatus@1 ASC NULLS LAST], preserve_partitioning=[true]
ProjectionExec: expr=[l_returnflag@0 as l_returnflag, l_linestatus@1 as l_linestatus, sum(lineitem.l_quantity)@2 as sum_qty, sum(lineitem.l_extendedprice)@3 as sum_base_price, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)@4 as sum_disc_price, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax)@5 as sum_charge, avg(lineitem.l_quantity)@6 as avg_qty, avg(lineitem.l_extendedprice)@7 as avg_price, avg(lineitem.l_discount)@8 as avg_disc, count(*)@9 as count_order]
AggregateExec: mode=FinalPartitioned, gby=[l_returnflag@0 as l_returnflag, l_linestatus@1 as l_linestatus], aggr=[sum(lineitem.l_quantity), sum(lineitem.l_extendedprice), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax), avg(lineitem.l_quantity), avg(lineitem.l_extendedprice), avg(lineitem.l_discount), count(*)]
CoalesceBatchesExec: target_batch_size=8192
FilterExec: l_shipdate@6 <= 1998-09-24
ParquetExec: file_groups={ ... }, projection=[l_quantity, l_extendedprice, l_discount, l_tax, l_returnflag, l_linestatus, l_shipdate], predicate=l_shipdate@10 <= 1998-09-24, pruning_predicate=CASE WHEN l_shipdate_null_count@1 = l_shipdate_row_count@2 THEN false ELSE l_shipdate_min@0 <= 1998-09-24 END, required_guarantees=[]
RepartitionExec: partitioning=Hash([l_returnflag@0, l_linestatus@1], 2), input_partitions=2
AggregateExec: mode=Partial, gby=[l_returnflag@5 as l_returnflag, l_linestatus@6 as l_linestatus], aggr=[sum(lineitem.l_quantity), sum(lineitem.l_extendedprice), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax), avg(lineitem.l_quantity), avg(lineitem.l_extendedprice), avg(lineitem.l_discount), count(*)]
ProjectionExec: expr=[l_extendedprice@1 * (Some(1),20,0 - l_discount@2) as __common_expr_2, l_quantity@0 as l_quantity, l_extendedprice@1 as l_extendedprice, l_discount@2 as l_discount, l_tax@3 as l_tax, l_returnflag@4 as l_returnflag, l_linestatus@5 as l_linestatus]
CoalesceBatchesExec: target_batch_size=8192
FilterExec: l_shipdate@6 <= 1998-09-24
ParquetExec: file_groups={ ... }, projection=[l_quantity, l_extendedprice, l_discount, l_tax, l_returnflag, l_linestatus, l_shipdate], predicate=l_shipdate@10 <= 1998-09-24, pruning_predicate=CASE WHEN l_shipdate_null_count@1 = l_shipdate_row_count@2 THEN false ELSE l_shipdate_min@0 <= 1998-09-24 END, required_guarantees=[]

RaySQL Plan
DataFusion Ray Distributed Plan
===========

Query Stage #0 (1 -> 1):
SortExec: expr=[l_returnflag@0 ASC NULLS LAST,l_linestatus@1 ASC NULLS LAST], preserve_partitioning=[false]
ProjectionExec: expr=[l_returnflag@0 as l_returnflag, l_linestatus@1 as l_linestatus, sum(lineitem.l_quantity)@2 as sum_qty, sum(lineitem.l_extendedprice)@3 as sum_base_price, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)@4 as sum_disc_price, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax)@5 as sum_charge, avg(lineitem.l_quantity)@6 as avg_qty, avg(lineitem.l_extendedprice)@7 as avg_price, avg(lineitem.l_discount)@8 as avg_disc, count(*)@9 as count_order]
AggregateExec: mode=Single, gby=[l_returnflag@5 as l_returnflag, l_linestatus@6 as l_linestatus], aggr=[sum(lineitem.l_quantity), sum(lineitem.l_extendedprice), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax), avg(lineitem.l_quantity), avg(lineitem.l_extendedprice), avg(lineitem.l_discount), count(*)]
ProjectionExec: expr=[l_extendedprice@1 * (Some(1),20,0 - l_discount@2) as __common_expr_2, l_quantity@0 as l_quantity, l_extendedprice@1 as l_extendedprice, l_discount@2 as l_discount, l_tax@3 as l_tax, l_returnflag@4 as l_returnflag, l_linestatus@5 as l_linestatus]
Query Stage #0 (2 -> 2):
ShuffleWriterExec(stage_id=0, output_partitioning=Hash([Column { name: "l_returnflag", index: 0 }, Column { name: "l_linestatus", index: 1 }], 2))
AggregateExec: mode=Partial, gby=[l_returnflag@5 as l_returnflag, l_linestatus@6 as l_linestatus], aggr=[sum(lineitem.l_quantity), sum(lineitem.l_extendedprice), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax), avg(lineitem.l_quantity), avg(lineitem.l_extendedprice), avg(lineitem.l_discount), count(*)]
ProjectionExec: expr=[l_extendedprice@1 * (Some(1),20,0 - l_discount@2) as __common_expr_2, l_quantity@0 as l_quantity, l_extendedprice@1 as l_extendedprice, l_discount@2 as l_discount, l_tax@3 as l_tax, l_returnflag@4 as l_returnflag, l_linestatus@5 as l_linestatus]
CoalesceBatchesExec: target_batch_size=8192
FilterExec: l_shipdate@6 <= 1998-09-24
ParquetExec: file_groups={ ... }, projection=[l_quantity, l_extendedprice, l_discount, l_tax, l_returnflag, l_linestatus, l_shipdate], predicate=l_shipdate@10 <= 1998-09-24, pruning_predicate=CASE WHEN l_shipdate_null_count@1 = l_shipdate_row_count@2 THEN false ELSE l_shipdate_min@0 <= 1998-09-24 END, required_guarantees=[]

Query Stage #1 (2 -> 2):
ShuffleWriterExec(stage_id=1, output_partitioning=Hash([Column { name: "l_returnflag", index: 0 }, Column { name: "l_linestatus", index: 1 }], 2))
SortExec: expr=[l_returnflag@0 ASC NULLS LAST,l_linestatus@1 ASC NULLS LAST], preserve_partitioning=[true]
ProjectionExec: expr=[l_returnflag@0 as l_returnflag, l_linestatus@1 as l_linestatus, sum(lineitem.l_quantity)@2 as sum_qty, sum(lineitem.l_extendedprice)@3 as sum_base_price, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)@4 as sum_disc_price, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax)@5 as sum_charge, avg(lineitem.l_quantity)@6 as avg_qty, avg(lineitem.l_extendedprice)@7 as avg_price, avg(lineitem.l_discount)@8 as avg_disc, count(*)@9 as count_order]
AggregateExec: mode=FinalPartitioned, gby=[l_returnflag@0 as l_returnflag, l_linestatus@1 as l_linestatus], aggr=[sum(lineitem.l_quantity), sum(lineitem.l_extendedprice), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax), avg(lineitem.l_quantity), avg(lineitem.l_extendedprice), avg(lineitem.l_discount), count(*)]
CoalesceBatchesExec: target_batch_size=8192
FilterExec: l_shipdate@6 <= 1998-09-24
ParquetExec: file_groups={ ... }, projection=[l_quantity, l_extendedprice, l_discount, l_tax, l_returnflag, l_linestatus, l_shipdate], predicate=l_shipdate@10 <= 1998-09-24, pruning_predicate=CASE WHEN l_shipdate_null_count@1 = l_shipdate_row_count@2 THEN false ELSE l_shipdate_min@0 <= 1998-09-24 END, required_guarantees=[]
ShuffleReaderExec(stage_id=0, input_partitioning=Hash([Column { name: "l_returnflag", index: 0 }, Column { name: "l_linestatus", index: 1 }], 2))

Query Stage #2 (2 -> 1):
SortPreservingMergeExec: [l_returnflag@0 ASC NULLS LAST,l_linestatus@1 ASC NULLS LAST]
ShuffleReaderExec(stage_id=1, input_partitioning=Hash([Column { name: "l_returnflag", index: 0 }, Column { name: "l_linestatus", index: 1 }], 2))

Loading
Loading