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

Jump to bottom

refactor: display input partitions for RepartitionExec #4969

Merged
merged 1 commit into from
Jan 19, 2023
Merged

refactor: display input partitions for RepartitionExec #4969

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
112 changes: 56 additions & 56 deletions datafusion/core/src/physical_optimizer/dist_enforcement.rs
View file
Open in desktop

Large diffs are not rendered by default.

28 changes: 14 additions & 14 deletions datafusion/core/src/physical_optimizer/repartition.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -495,7 +495,7 @@ mod tests {
"AggregateExec: mode=Final, gby=[], aggr=[]",
"CoalescePartitionsExec",
"AggregateExec: mode=Partial, gby=[], aggr=[]",
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"ParquetExec: limit=None, partitions={1 group: [[x]]}, projection=[c1]",
];

Expand All @@ -512,7 +512,7 @@ mod tests {
"CoalescePartitionsExec",
"AggregateExec: mode=Partial, gby=[], aggr=[]",
"FilterExec: c1@0",
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"ParquetExec: limit=None, partitions={1 group: [[x]]}, projection=[c1]",
];

Expand All @@ -530,7 +530,7 @@ mod tests {
"LocalLimitExec: fetch=100",
"FilterExec: c1@0",
// nothing sorts the data, so the local limit doesn't require sorted data either
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"ParquetExec: limit=None, partitions={1 group: [[x]]}, projection=[c1]",
];

Expand All @@ -548,7 +548,7 @@ mod tests {
"LocalLimitExec: fetch=100",
"FilterExec: c1@0",
// nothing sorts the data, so the local limit doesn't require sorted data either
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"ParquetExec: limit=None, partitions={1 group: [[x]]}, projection=[c1]",
];

Expand Down Expand Up @@ -598,13 +598,13 @@ mod tests {
"AggregateExec: mode=Final, gby=[], aggr=[]",
"CoalescePartitionsExec",
"AggregateExec: mode=Partial, gby=[], aggr=[]",
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"GlobalLimitExec: skip=0, fetch=100",
"CoalescePartitionsExec",
"LocalLimitExec: fetch=100",
"FilterExec: c1@0",
// repartition should happen prior to the filter to maximize parallelism
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"GlobalLimitExec: skip=0, fetch=100",
"LocalLimitExec: fetch=100",
// Expect no repartition to happen for local limit
Expand All @@ -625,13 +625,13 @@ mod tests {
"AggregateExec: mode=Final, gby=[], aggr=[]",
"CoalescePartitionsExec",
"AggregateExec: mode=Partial, gby=[], aggr=[]",
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"GlobalLimitExec: skip=5, fetch=100",
"CoalescePartitionsExec",
"LocalLimitExec: fetch=100",
"FilterExec: c1@0",
// repartition should happen prior to the filter to maximize parallelism
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"GlobalLimitExec: skip=0, fetch=100",
"LocalLimitExec: fetch=100",
// Expect no repartition to happen for local limit
Expand Down Expand Up @@ -671,7 +671,7 @@ mod tests {
let expected = &[
"SortPreservingMergeExec: [c1@0 ASC]",
"SortExec: [c1@0 ASC]",
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"ParquetExec: limit=None, partitions={1 group: [[x]]}, projection=[c1]",
];

Expand Down Expand Up @@ -754,7 +754,7 @@ mod tests {
"ParquetExec: limit=None, partitions={1 group: [[x]]}, output_ordering=[c1@0 ASC], projection=[c1]",
// union input 2: should repartition
"FilterExec: c1@0",
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"ParquetExec: limit=None, partitions={1 group: [[x]]}, projection=[c1]",
];

Expand All @@ -772,7 +772,7 @@ mod tests {
"SortPreservingMergeExec: [c1@0 ASC]",
"SortExec: [c1@0 ASC]",
"ProjectionExec: expr=[c1@0 as c1]",
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"ParquetExec: limit=None, partitions={1 group: [[x]]}, projection=[c1]",
];

Expand Down Expand Up @@ -806,7 +806,7 @@ mod tests {
// Expect repartition on the input to the sort (as it can benefit from additional parallelism)
"SortExec: [c1@0 ASC]",
"ProjectionExec: expr=[c1@0 as c1]",
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"ParquetExec: limit=None, partitions={1 group: [[x]]}, projection=[c1]",
];

Expand All @@ -824,7 +824,7 @@ mod tests {
// Expect repartition on the input to the sort (as it can benefit from additional parallelism)
"SortExec: [c1@0 ASC]",
"FilterExec: c1@0",
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"ParquetExec: limit=None, partitions={1 group: [[x]]}, projection=[c1]",
];

Expand All @@ -846,7 +846,7 @@ mod tests {
"ProjectionExec: expr=[c1@0 as c1]",
"FilterExec: c1@0",
// repartition is lowest down
"RepartitionExec: partitioning=RoundRobinBatch(10)",
"RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
"ParquetExec: limit=None, partitions={1 group: [[x]]}, projection=[c1]",
];

Expand Down
2 changes: 1 addition & 1 deletion datafusion/core/src/physical_plan/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -322,7 +322,7 @@ pub fn with_new_children_if_necessary(
/// assert_eq!("ProjectionExec: expr=[a@0 as a]\
/// \n CoalesceBatchesExec: target_batch_size=8192\
/// \n FilterExec: a@0 < 5\
/// \n RepartitionExec: partitioning=RoundRobinBatch(3)\
/// \n RepartitionExec: partitioning=RoundRobinBatch(3), input_partitions=1\
/// \n CsvExec: files={1 group: [[WORKING_DIR/tests/data/example.csv]]}, has_header=true, limit=None, projection=[a]",
/// plan_string.trim());
///
Expand Down
7 changes: 6 additions & 1 deletion datafusion/core/src/physical_plan/repartition/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -445,7 +445,12 @@ impl ExecutionPlan for RepartitionExec {
) -> std::fmt::Result {
match t {
DisplayFormatType::Default => {
write!(f, "RepartitionExec: partitioning={:?}", self.partitioning)
write!(
f,
"RepartitionExec: partitioning={:?}, input_partitions={}",
self.partitioning,
self.input.output_partitioning().partition_count()
)
}
}
}
Expand Down
2 changes: 1 addition & 1 deletion datafusion/core/tests/sql/avro.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,7 +150,7 @@ async fn avro_explain() {
\n AggregateExec: mode=Final, gby=[], aggr=[COUNT(UInt8(1))]\
\n CoalescePartitionsExec\
\n AggregateExec: mode=Partial, gby=[], aggr=[COUNT(UInt8(1))]\
\n RepartitionExec: partitioning=RoundRobinBatch(NUM_CORES)\
\n RepartitionExec: partitioning=RoundRobinBatch(NUM_CORES), input_partitions=1\
\n AvroExec: files={1 group: [[ARROW_TEST_DATA/avro/alltypes_plain.avro]]}, limit=None\
\n",
],
Expand Down
14 changes: 7 additions & 7 deletions datafusion/core/tests/sql/explain_analyze.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -612,11 +612,11 @@ async fn test_physical_plan_display_indent() {
" ProjectionExec: expr=[c1@0 as c1, MAX(aggregate_test_100.c12)@1 as MAX(aggregate_test_100.c12), MIN(aggregate_test_100.c12)@2 as the_min]",
" AggregateExec: mode=FinalPartitioned, gby=[c1@0 as c1], aggr=[MAX(aggregate_test_100.c12), MIN(aggregate_test_100.c12)]",
" CoalesceBatchesExec: target_batch_size=4096",
" RepartitionExec: partitioning=Hash([Column { name: \"c1\", index: 0 }], 9000)",
" RepartitionExec: partitioning=Hash([Column { name: \"c1\", index: 0 }], 9000), input_partitions=9000",
" AggregateExec: mode=Partial, gby=[c1@0 as c1], aggr=[MAX(aggregate_test_100.c12), MIN(aggregate_test_100.c12)]",
" CoalesceBatchesExec: target_batch_size=4096",
" FilterExec: c12@1 < 10",
" RepartitionExec: partitioning=RoundRobinBatch(9000)",
" RepartitionExec: partitioning=RoundRobinBatch(9000), input_partitions=1",
" CsvExec: files={1 group: [[ARROW_TEST_DATA/csv/aggregate_test_100.csv]]}, has_header=true, limit=None, projection=[c1, c12]",
];

Expand Down Expand Up @@ -656,14 +656,14 @@ async fn test_physical_plan_display_indent_multi_children() {
" CoalesceBatchesExec: target_batch_size=4096",
" HashJoinExec: mode=Partitioned, join_type=Inner, on=[(Column { name: \"c1\", index: 0 }, Column { name: \"c2\", index: 0 })]",
" CoalesceBatchesExec: target_batch_size=4096",
" RepartitionExec: partitioning=Hash([Column { name: \"c1\", index: 0 }], 9000)",
" RepartitionExec: partitioning=Hash([Column { name: \"c1\", index: 0 }], 9000), input_partitions=9000",
" ProjectionExec: expr=[c1@0 as c1]",
" RepartitionExec: partitioning=RoundRobinBatch(9000)",
" RepartitionExec: partitioning=RoundRobinBatch(9000), input_partitions=1",
" CsvExec: files={1 group: [[ARROW_TEST_DATA/csv/aggregate_test_100.csv]]}, has_header=true, limit=None, projection=[c1]",
" CoalesceBatchesExec: target_batch_size=4096",
" RepartitionExec: partitioning=Hash([Column { name: \"c2\", index: 0 }], 9000)",
" RepartitionExec: partitioning=Hash([Column { name: \"c2\", index: 0 }], 9000), input_partitions=9000",
" ProjectionExec: expr=[c1@0 as c2]",
" RepartitionExec: partitioning=RoundRobinBatch(9000)",
" RepartitionExec: partitioning=RoundRobinBatch(9000), input_partitions=1",
" CsvExec: files={1 group: [[ARROW_TEST_DATA/csv/aggregate_test_100.csv]]}, has_header=true, limit=None, projection=[c1]",
];

Expand Down Expand Up @@ -705,7 +705,7 @@ async fn csv_explain() {
"ProjectionExec: expr=[c1@0 as c1]\
\n CoalesceBatchesExec: target_batch_size=4096\
\n FilterExec: c2@1 > 10\
\n RepartitionExec: partitioning=RoundRobinBatch(NUM_CORES)\
\n RepartitionExec: partitioning=RoundRobinBatch(NUM_CORES), input_partitions=1\
\n CsvExec: files={1 group: [[ARROW_TEST_DATA/csv/aggregate_test_100.csv]]}, has_header=true, limit=None, projection=[c1, c2]\
\n",
]];
Expand Down
Loading