This is an automated email from the ASF dual-hosted git repository.
alamb pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion.git
The following commit(s) were added to refs/heads/main by this push:
new bed57df3e8 [MINOR]: Move pipeline checker rule to the end (#10502)
bed57df3e8 is described below
commit bed57df3e8dc04961755da593d345c61d0e1be39
Author: Mustafa Akur <[email protected]>
AuthorDate: Wed May 15 21:52:25 2024 +0300
[MINOR]: Move pipeline checker rule to the end (#10502)
* Move pipeline checker to last
* Update slt
---
datafusion/core/src/physical_optimizer/optimizer.rs | 10 +++++-----
datafusion/sqllogictest/test_files/explain.slt | 6 +++---
2 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/datafusion/core/src/physical_optimizer/optimizer.rs
b/datafusion/core/src/physical_optimizer/optimizer.rs
index 08cbf68fa6..416985983d 100644
--- a/datafusion/core/src/physical_optimizer/optimizer.rs
+++ b/datafusion/core/src/physical_optimizer/optimizer.rs
@@ -112,11 +112,6 @@ impl PhysicalOptimizer {
// Remove the ancillary output requirement operator since we are
done with the planning
// phase.
Arc::new(OutputRequirements::new_remove_mode()),
- // The PipelineChecker rule will reject non-runnable query plans
that use
- // pipeline-breaking operators on infinite input(s). The rule
generates a
- // diagnostic error message when this happens. It makes no changes
to the
- // given query plan; i.e. it only acts as a final gatekeeping rule.
- Arc::new(PipelineChecker::new()),
// The aggregation limiter will try to find situations where the
accumulator count
// is not tied to the cardinality, i.e. when the output of the
aggregation is passed
// into an `order by max(x) limit y`. In this case it will copy
the limit value down
@@ -129,6 +124,11 @@ impl PhysicalOptimizer {
// are not present, the load of executors such as join or union
will be
// reduced by narrowing their input tables.
Arc::new(ProjectionPushdown::new()),
+ // The PipelineChecker rule will reject non-runnable query plans
that use
+ // pipeline-breaking operators on infinite input(s). The rule
generates a
+ // diagnostic error message when this happens. It makes no changes
to the
+ // given query plan; i.e. it only acts as a final gatekeeping rule.
+ Arc::new(PipelineChecker::new()),
];
Self::with_rules(rules)
diff --git a/datafusion/sqllogictest/test_files/explain.slt
b/datafusion/sqllogictest/test_files/explain.slt
index 3a4ac747eb..92c537f975 100644
--- a/datafusion/sqllogictest/test_files/explain.slt
+++ b/datafusion/sqllogictest/test_files/explain.slt
@@ -252,9 +252,9 @@ physical_plan after OptimizeAggregateOrder SAME TEXT AS
ABOVE
physical_plan after ProjectionPushdown SAME TEXT AS ABOVE
physical_plan after coalesce_batches SAME TEXT AS ABOVE
physical_plan after OutputRequirements CsvExec: file_groups={1 group:
[[WORKSPACE_ROOT/datafusion/core/tests/data/example.csv]]}, projection=[a, b,
c], has_header=true
-physical_plan after PipelineChecker SAME TEXT AS ABOVE
physical_plan after LimitAggregation SAME TEXT AS ABOVE
physical_plan after ProjectionPushdown SAME TEXT AS ABOVE
+physical_plan after PipelineChecker SAME TEXT AS ABOVE
physical_plan CsvExec: file_groups={1 group:
[[WORKSPACE_ROOT/datafusion/core/tests/data/example.csv]]}, projection=[a, b,
c], has_header=true
physical_plan_with_stats CsvExec: file_groups={1 group:
[[WORKSPACE_ROOT/datafusion/core/tests/data/example.csv]]}, projection=[a, b,
c], has_header=true, statistics=[Rows=Absent, Bytes=Absent,
[(Col[0]:),(Col[1]:),(Col[2]:)]]
@@ -311,9 +311,9 @@ physical_plan after coalesce_batches SAME TEXT AS ABOVE
physical_plan after OutputRequirements
01)GlobalLimitExec: skip=0, fetch=10, statistics=[Rows=Exact(8), Bytes=Absent,
[(Col[0]:),(Col[1]:),(Col[2]:),(Col[3]:),(Col[4]:),(Col[5]:),(Col[6]:),(Col[7]:),(Col[8]:),(Col[9]:),(Col[10]:)]]
02)--ParquetExec: file_groups={1 group:
[[WORKSPACE_ROOT/parquet-testing/data/alltypes_plain.parquet]]},
projection=[id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col], limit=10,
statistics=[Rows=Exact(8), Bytes=Absent,
[(Col[0]:),(Col[1]:),(Col[2]:),(Col[3]:),(Col[4]:),(Col[5]:),(Col[6]:),(Col[7]:),(Col[8]:),(Col[9]:),(Col[10]:)]]
-physical_plan after PipelineChecker SAME TEXT AS ABOVE
physical_plan after LimitAggregation SAME TEXT AS ABOVE
physical_plan after ProjectionPushdown SAME TEXT AS ABOVE
+physical_plan after PipelineChecker SAME TEXT AS ABOVE
physical_plan
01)GlobalLimitExec: skip=0, fetch=10, statistics=[Rows=Exact(8), Bytes=Absent,
[(Col[0]:),(Col[1]:),(Col[2]:),(Col[3]:),(Col[4]:),(Col[5]:),(Col[6]:),(Col[7]:),(Col[8]:),(Col[9]:),(Col[10]:)]]
02)--ParquetExec: file_groups={1 group:
[[WORKSPACE_ROOT/parquet-testing/data/alltypes_plain.parquet]]},
projection=[id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col], limit=10,
statistics=[Rows=Exact(8), Bytes=Absent,
[(Col[0]:),(Col[1]:),(Col[2]:),(Col[3]:),(Col[4]:),(Col[5]:),(Col[6]:),(Col[7]:),(Col[8]:),(Col[9]:),(Col[10]:)]]
@@ -348,9 +348,9 @@ physical_plan after coalesce_batches SAME TEXT AS ABOVE
physical_plan after OutputRequirements
01)GlobalLimitExec: skip=0, fetch=10
02)--ParquetExec: file_groups={1 group:
[[WORKSPACE_ROOT/parquet-testing/data/alltypes_plain.parquet]]},
projection=[id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col], limit=10
-physical_plan after PipelineChecker SAME TEXT AS ABOVE
physical_plan after LimitAggregation SAME TEXT AS ABOVE
physical_plan after ProjectionPushdown SAME TEXT AS ABOVE
+physical_plan after PipelineChecker SAME TEXT AS ABOVE
physical_plan
01)GlobalLimitExec: skip=0, fetch=10
02)--ParquetExec: file_groups={1 group:
[[WORKSPACE_ROOT/parquet-testing/data/alltypes_plain.parquet]]},
projection=[id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col], limit=10
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
