feat(promql): execute zero-input scalar roots through fused children

Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com>
This commit is contained in:
discord9
2026-10-26 00:13:13 +08:00
parent 9720e1bf88
commit 5bcd96cead
12 changed files with 715 additions and 52 deletions
+4
View File
@@ -77,6 +77,10 @@ operators. Statement-to-plan translation lives in `src/query/src/promql/`.
its doc is written for a caller that does not exist.
- **A native window requires non-interleaved input.** Only `Contiguous` and
`KeyThenTime` are accepted; `Interleaved` is refused when compiled.
- **A fused tree runs ordinary raw children and a literal Scalar root.** Recursive native
execution keeps `source_index` routing for one or more raw children; only a validated
zero-source Scalar root is materialized on its bound grid without a scanner. It must not
displace the current multi-input vector path or the single-input partial aggregate path.
- **A series closes exactly once**, on the chunk that says so — per input series,
not per label set. A node that rewrites labels can hand two input series over
under one label set, and each closes on its own chunk, so a label set may be
+75 -25
View File
@@ -56,6 +56,7 @@ use datafusion::execution::context::TaskContext;
use datafusion::execution::memory_pool::{MemoryReservation, UnboundedMemoryPool};
use datafusion::logical_expr::{Expr, LogicalPlan, UserDefinedLogicalNodeCore};
use datafusion::physical_expr::{EquivalenceProperties, PhysicalExpr};
use datafusion::physical_plan::execution_plan::{Boundedness, EmissionType};
use datafusion::physical_plan::metrics::{ExecutionPlanMetricsSet, MetricsSet};
use datafusion::physical_plan::stream::RecordBatchStreamAdapter;
use datafusion::physical_plan::{
@@ -498,6 +499,14 @@ fn validate_binding(
)));
}
let schemas = collect_source_schemas(tree)?;
if schemas.is_empty()
&& (!matches!(tree.root().expr, NativeExpr::Scalar(_))
|| !matches!(tree.root().output, NativeType::Scalar(_)))
{
return Err(DataFusionError::Plan(
"FusedSeries without inputs requires a constant scalar root".into(),
));
}
if schemas.len() != child_count {
return Err(DataFusionError::Plan(
"FusedSeries source indexes must densely match its children".into(),
@@ -570,17 +579,7 @@ pub(crate) fn tree_source_fields(tree: &NativeTree) -> DataFusionResult<Vec<Vec<
fn validate_physical_tree(tree: &NativeTree) -> DataFusionResult<Vec<Arc<SeriesSchema>>> {
let schemas = collect_source_schemas(tree)?;
if schemas.is_empty() {
return Err(DataFusionError::Plan(
"FusedSeries physical plan requires at least one raw source".into(),
));
}
if !tree
.root()
.output
.samples()
.is_some_and(|schema| schema.eval_grid.is_some())
{
if tree.root().output.grid().is_none() {
return Err(DataFusionError::Plan(
"FusedSeries output is not evaluated samples".into(),
));
@@ -599,6 +598,37 @@ pub(crate) enum OutputColumn {
Tag(usize),
}
/// The caller-named value field used by the ordinary row conversion for a label-free scalar.
fn scalar_root_fields(
output_schema: &SchemaRef,
tags: &[String],
time_column: &str,
) -> DataFusionResult<Vec<FieldSpec>> {
if !tags.is_empty() {
return Err(DataFusionError::Plan(format!(
"FusedSeriesExec scalar root cannot produce {} tag columns",
tags.len()
)));
}
let mut values = output_schema
.fields()
.iter()
.filter(|field| field.name().as_str() != time_column);
let Some(value) = values.next() else {
return Err(DataFusionError::Plan(
"missing value column in scalar root output schema".to_string(),
));
};
if values.next().is_some() {
return Err(DataFusionError::Plan(
"scalar root output schema must contain exactly one value column".into(),
));
}
Ok(vec![FieldSpec {
name: Arc::from(value.name().as_str()),
}])
}
/// Classifies every output column, rejecting anything the conversion cannot produce.
pub(crate) fn classify_output(
output_schema: &SchemaRef,
@@ -789,7 +819,7 @@ impl FusedSeriesExec {
partial_fold: Option<BoundAggregate>,
) -> DataFusionResult<Self> {
let raw_schemas = validate_physical_tree(&tree)?;
if inputs.len() != raw_schemas.len() || inputs.is_empty() {
if inputs.len() != raw_schemas.len() {
return Err(DataFusionError::Plan(format!(
"FusedSeries physical input count {} does not match its {} raw sources",
inputs.len(),
@@ -798,11 +828,8 @@ impl FusedSeriesExec {
}
// Building a state proves the runtime executes this tree; drop the validation state now.
let _ = NativeExecutionState::try_new(&tree, Arc::new(UnboundedMemoryPool::default()))?;
let output_series = tree
.root()
.output
.samples()
.ok_or_else(|| DataFusionError::Plan("FusedSeries output is not samples".into()))?;
let output_series = tree.root().output.samples();
let scalar_root = raw_schemas.is_empty();
if let Some(op) = &partial_fold {
aggregate_op(op)?;
}
@@ -827,15 +854,24 @@ impl FusedSeriesExec {
}
let classification = if partial_fold.is_some() {
Vec::new()
} else if scalar_root {
let scalar_fields = scalar_root_fields(&output_schema, &output_tags, &time_column)?;
classify_output(&output_schema, &scalar_fields, &output_tags, &time_column)?
} else {
classify_output(
&output_schema,
&output_series.fields,
&output_series
.ok_or_else(|| {
DataFusionError::Plan("FusedSeries output is not samples".into())
})?
.fields,
&output_tags,
&time_column,
)?
};
let partition_count = inputs[0].0.properties().partitioning.partition_count();
let partition_count = inputs.first().map_or(1, |(input, _, _)| {
input.properties().partitioning.partition_count()
});
for (index, (input, label_source, ordering)) in inputs.iter().enumerate() {
let count = input.properties().partitioning.partition_count();
if count == 0 {
@@ -868,9 +904,19 @@ impl FusedSeriesExec {
}
let properties = Arc::new(PlanProperties::new(
EquivalenceProperties::new(output_schema.clone()),
Partitioning::UnknownPartitioning(if inputs.len() > 1 { 1 } else { partition_count }),
inputs[0].0.properties().emission_type,
inputs[0].0.properties().boundedness,
Partitioning::UnknownPartitioning(if inputs.len() != 1 {
1
} else {
partition_count
}),
inputs.first().map_or(EmissionType::Final, |(input, _, _)| {
input.properties().emission_type
}),
inputs
.first()
.map_or(Boundedness::Bounded, |(input, _, _)| {
input.properties().boundedness
}),
));
Ok(Self {
promql,
@@ -989,9 +1035,9 @@ impl ExecutionPlan for FusedSeriesExec {
partition: usize,
context: Arc<TaskContext>,
) -> DataFusionResult<SendableRecordBatchStream> {
if self.inputs.len() > 1 && partition != 0 {
if partition >= self.properties.partitioning.partition_count() {
return Err(DataFusionError::Execution(
"multi-source FusedSeries only has output partition 0".into(),
"FusedSeries output partition is out of range".into(),
));
}
let state = NativeExecutionState::try_new(
@@ -1047,9 +1093,13 @@ impl ExecutionPlan for FusedSeriesExec {
)
})
.transpose()?;
let mut executor = NativeExecutor::new(state);
if streams.is_empty() {
executor.end_of_input()?;
}
Ok(Box::pin(FusedSeriesStream {
inputs: streams,
executor: Some(NativeExecutor::new(state)),
executor: Some(executor),
input_ids,
classification: Arc::clone(&self.classification),
tags: Arc::clone(&self.tags),
@@ -1900,14 +1900,238 @@ async fn later_source_error_drops_all_gathered_inputs() {
assert_eq!(0, pool.reserved());
}
/// The physical boundary rejects zero sources and mismatched physical source counts.
/// A literal scalar runs as one schema-checked, one-partition output without scan children.
#[tokio::test]
async fn physical_plan_accepts_scalar_root_without_sources() {
let statement_grid = grid();
let tree = scalar_tree(Arc::clone(&statement_grid), 4.0);
let binding = FusedSeriesBinding {
grid: statement_grid,
metric_name: None,
time_index: TIME.to_string(),
tags: vec![],
};
let schema = Arc::new(Schema::new(vec![
Field::new(VALUE, DataType::Float64, true),
Field::new(
TIME,
DataType::Timestamp(TimeUnit::Millisecond, None),
false,
),
]));
let node = FusedSeries::try_new(
Arc::from("4"),
tree,
binding.clone(),
Vec::new(),
schema.to_dfschema_ref().unwrap(),
)
.unwrap();
let exec = node.to_execution_plan(Vec::new()).unwrap();
assert_eq!(1, exec.properties().output_partitioning().partition_count());
let rebuilt = exec.clone().with_new_children(Vec::new()).unwrap();
assert!(matches!(
exec.properties().boundedness,
Boundedness::Bounded
));
assert!(exec.children().is_empty());
assert!(rebuilt.children().is_empty());
let zero_pool = Arc::new(GreedyMemoryPool::new(0));
let mut rejected = exec.execute(0, task_context(&zero_pool)).unwrap();
assert!(rejected.next().await.unwrap().is_err());
drop(rejected);
assert_eq!(0, zero_pool.reserved());
let pool = Arc::new(GreedyMemoryPool::new(1 << 20));
let mut stream = exec.execute(0, task_context(&pool)).unwrap();
let first = stream.next().await.unwrap().unwrap();
assert!(stream.next().await.is_none());
assert!(stream.next().await.is_none());
drop(stream);
let batches = vec![first];
assert_eq!(1, batches.len());
assert_eq!(schema.as_ref(), batches[0].schema().as_ref());
assert_eq!(GRID_LEN as usize, batches[0].num_rows());
let timestamps = batches[0]
.column_by_name(TIME)
.unwrap()
.as_any()
.downcast_ref::<TimestampMillisecondArray>()
.unwrap();
assert_eq!(grid_timestamps(), timestamps.values().as_ref());
let values = batches[0]
.column_by_name(VALUE)
.unwrap()
.as_any()
.downcast_ref::<Float64Array>()
.unwrap();
assert!(values.iter().all(|value| value == Some(4.0)));
assert_eq!(0, pool.reserved());
let rebuilt_pool = Arc::new(GreedyMemoryPool::new(1 << 20));
let rebuilt_batches = rebuilt
.execute(0, task_context(&rebuilt_pool))
.unwrap()
.try_collect::<Vec<_>>()
.await
.unwrap();
assert_eq!(1, rebuilt_batches.len());
assert_eq!(batches[0].schema(), rebuilt_batches[0].schema());
assert_eq!(batches[0].columns(), rebuilt_batches[0].columns());
assert_eq!(0, rebuilt_pool.reserved());
let drop_pool = Arc::new(GreedyMemoryPool::new(1 << 20));
let unpolled = rebuilt.execute(0, task_context(&drop_pool)).unwrap();
drop(unpolled);
assert_eq!(0, drop_pool.reserved());
let mut early = rebuilt.execute(0, task_context(&drop_pool)).unwrap();
let early_batch = early.next().await.unwrap().unwrap();
drop(early);
assert_eq!(0, drop_pool.reserved());
drop(early_batch);
assert_eq!(0, drop_pool.reserved());
assert!(exec.execute(1, task_context(&pool)).is_err());
let metrics = exec.metrics().unwrap();
assert_eq!(1, count(&metrics, "native.root.output_batches"));
assert_eq!(
GRID_LEN as usize,
count(&metrics, "native.root.output_values")
);
assert_eq!(
GRID_LEN as usize,
count(&metrics, "native.root.evaluated_grid_points")
);
assert_eq!(1, count(&metrics, "native.root.completed_series"));
assert_eq!(0, count(&metrics, "native.root.input_batches"));
assert_eq!(0, count(&metrics, "native.root.input_samples"));
let partial_error = FusedSeries::try_new_partial(
Arc::from("4"),
scalar_tree(grid(), 4.0),
binding,
vec![],
partial_op(AggregateKind::Sum, &[]),
)
.expect_err("scalar roots cannot be partial folds");
assert!(partial_error.to_string().contains("one raw child"));
}
#[tokio::test]
async fn physical_scalar_rejects_malformed_output_schema() {
let tree = scalar_tree(grid(), 4.0);
let binding = FusedSeriesBinding {
grid: grid(),
metric_name: None,
time_index: TIME.to_string(),
tags: vec![],
};
let schemas = [
Schema::new(vec![Field::new(
TIME,
DataType::Timestamp(TimeUnit::Millisecond, None),
false,
)]),
Schema::new(vec![Field::new(VALUE, DataType::Float64, true)]),
Schema::new(vec![
Field::new(VALUE, DataType::Float64, true),
Field::new(OTHER, DataType::Float64, true),
Field::new(
TIME,
DataType::Timestamp(TimeUnit::Millisecond, None),
false,
),
]),
Schema::new(vec![
Field::new(VALUE, DataType::Utf8, true),
Field::new(
TIME,
DataType::Timestamp(TimeUnit::Millisecond, None),
false,
),
]),
Schema::new(vec![
Field::new(VALUE, DataType::Float64, true),
Field::new(TIME, DataType::Float64, false),
]),
];
for schema in schemas {
let node = FusedSeries::try_new(
Arc::from("4"),
tree.clone(),
binding.clone(),
Vec::new(),
Arc::new(schema).to_dfschema_ref().unwrap(),
)
.unwrap();
assert!(node.to_execution_plan(Vec::new()).is_err());
}
let tagged = FusedSeries::try_new(
Arc::from("4"),
tree,
FusedSeriesBinding {
tags: vec![HOST.to_string()],
..binding
},
Vec::new(),
output_schema().to_dfschema_ref().unwrap(),
)
.unwrap();
assert!(tagged.to_execution_plan(Vec::new()).is_err());
}
#[tokio::test]
async fn physical_scalar_conversion_preserves_special_float_bits() {
for value in [f64::NAN, -0.0, f64::INFINITY, f64::NEG_INFINITY] {
let statement_grid = grid();
let tree = scalar_tree(Arc::clone(&statement_grid), value);
let binding = FusedSeriesBinding {
grid: statement_grid,
metric_name: None,
time_index: TIME.to_string(),
tags: vec![],
};
let schema = Arc::new(Schema::new(vec![
Field::new(VALUE, DataType::Float64, true),
Field::new(
TIME,
DataType::Timestamp(TimeUnit::Millisecond, None),
false,
),
]));
let node = FusedSeries::try_new(
Arc::from("4"),
tree,
binding,
Vec::new(),
schema.to_dfschema_ref().unwrap(),
)
.unwrap();
let exec = node.to_execution_plan(Vec::new()).unwrap();
let batches = exec
.execute(0, SessionContext::default().task_ctx())
.unwrap()
.try_collect::<Vec<_>>()
.await
.unwrap();
assert_eq!(1, batches.len());
assert_eq!(GRID_LEN as usize, batches[0].num_rows());
let actual = batches[0]
.column_by_name(VALUE)
.unwrap()
.as_any()
.downcast_ref::<Float64Array>()
.unwrap();
assert!(
actual
.iter()
.all(|actual| actual.unwrap().to_bits() == value.to_bits())
);
}
}
#[test]
fn physical_plan_requires_matching_source_count() {
let node = fused(rate_tree());
let zero = node
.to_execution_plan(Vec::new())
.expect_err("physical execution cannot run with zero sources");
assert!(zero.to_string().contains("source") || zero.to_string().contains("input"));
.expect_err("a raw-series tree cannot run with zero sources");
assert!(zero.to_string().contains("count") || zero.to_string().contains("source"));
let source = memory_exec(Vec::new());
let tuple = || {
+4 -1
View File
@@ -109,11 +109,14 @@ fn plan_fused_series(
physical_inputs: &[Arc<dyn ExecutionPlan>],
target_partitions: usize,
) -> DfResult<Option<Arc<dyn ExecutionPlan>>> {
if physical_inputs.len() != fused.children().len() || physical_inputs.is_empty() {
if physical_inputs.len() != fused.children().len() {
return Err(DataFusionError::Plan(
"FusedSeries physical child count mismatch".into(),
));
}
if physical_inputs.is_empty() {
return fused.to_execution_plan(Vec::new()).map(Some);
}
if physical_inputs
.iter()
.any(|input| input.downcast_ref::<RegionScanExec>().is_none())
+84 -11
View File
@@ -30,7 +30,7 @@ use datatypes::arrow::buffer::{Buffer, ScalarBuffer};
use datatypes::series::histogram::HistogramView;
use datatypes::series::raw::{RawSeriesChunk, RawTimestamps};
use datatypes::series::samples::{
DenseSamplesRef, RowCursor, SampleRef, Samples, Series, SeriesFields, SeriesSchema,
DenseSamplesRef, FieldSpec, RowCursor, SampleRef, Samples, Series, SeriesFields, SeriesSchema,
};
use datatypes::series::time::{EvalGrid, GridRange, GridSpan, GridSpec, TimeAxis};
use datatypes::series::{SeriesLabels, SeriesOrdering};
@@ -1974,6 +1974,24 @@ fn grid_position(grid: &EvalGrid, timestamp: i64) -> Result<usize> {
Ok(position as usize)
}
/// One unlabelled constant value per statement grid point, closed on its only chunk.
fn scalar_chunk(grid: Arc<EvalGrid>, value: f64) -> Result<EvaluatedChunk> {
let schema = SeriesSchema {
fields: Arc::from([FieldSpec {
name: "value".into(),
}]),
eval_grid: Some(Arc::clone(&grid)),
};
let len = grid.spec().len as usize;
let time = GridRange::try_new(grid, 0, len).map_err(series_error)?;
let values = Float64Array::from(vec![value; len]);
let fields = SeriesFields::one(Samples::from_float(values));
let metric = SeriesLabels::try_new(None, Vec::new()).map_err(series_error)?;
let series =
Series::try_new(&schema, metric, TimeAxis::Grid(time), fields).map_err(series_error)?;
EvaluatedChunk::try_new(series, true)
}
/// A closing chunk carrying `metric` and no row at all.
///
/// A series whose selection picked no source row still closes exactly once, on a chunk that holds
@@ -2068,6 +2086,8 @@ struct InputSlot {
pub struct NativeExecutionState {
root: RuntimeNode,
inputs: Vec<InputSlot>,
/// A constant root waiting for its only pull; operand scalars remain chunkless.
scalar_root: Option<(Arc<EvalGrid>, f64, NodeState)>,
}
impl NodeState {
@@ -2834,25 +2854,46 @@ impl NativeExecutionState {
pub fn try_new(tree: &NativeTree, pool: Arc<dyn MemoryPool>) -> Result<Self> {
let mut inputs = Vec::new();
let (root, _) = RuntimeNode::build(tree.root(), &pool, &mut inputs)?;
match tree.root().output.samples() {
Some(schema) if schema.eval_grid.is_some() => {}
Some(_) => {
let scalar_root = if inputs.is_empty() {
match (&tree.root().expr, &tree.root().output) {
(NativeExpr::Scalar(BoundScalar { value }), NativeType::Scalar(grid)) => Some((
Arc::clone(grid),
*value,
NodeState::new("native.scalar", Arc::clone(&root.metrics), &pool),
)),
_ => {
return Err(DataFusionError::Execution(
"native tree without inputs must be a scalar root".into(),
));
}
}
} else {
None
};
match &tree.root().output {
NativeType::Scalar(_) if inputs.is_empty() => {}
NativeType::Scalar(_) => {
return Err(DataFusionError::Execution(
"native scalar root unexpectedly has input nodes".into(),
));
}
NativeType::Samples(schema) if schema.eval_grid.is_some() => {}
NativeType::Samples(_) => {
return Err(DataFusionError::Execution(
"native runtime root produces raw samples".to_string(),
));
}
None => {
NativeType::AggregateState(_) => {
return Err(DataFusionError::Execution(
"native runtime root produces no sample output".to_string(),
));
}
}
if inputs.is_empty() {
return Err(DataFusionError::Execution(
"native tree has no input node".to_string(),
));
}
Ok(Self { root, inputs })
Ok(Self {
root,
inputs,
scalar_root,
})
}
/// Registers the metric handles of every node of this execution's tree with `set`.
@@ -2879,6 +2920,11 @@ impl NativeExecutionState {
.map(|slot| slot.state.buffer.reservation.size())
.fold(0usize, usize::saturating_add)
.saturating_add(self.root.reserved_bytes())
.saturating_add(
self.scalar_root
.as_ref()
.map_or(0, |(_, _, state)| state.buffer.reservation.size()),
)
}
}
@@ -2894,6 +2940,27 @@ impl NativeExecutionState {
/// `inputs_finished` is the caller's word that no more source chunks will arrive; it is passed
/// down unchanged, because only a node that reads its whole input needs it.
fn pull(&mut self, inputs_finished: bool) -> Result<Option<NativeChunk>> {
if let Some((grid, value, mut state)) = self.scalar_root.take() {
let len = usize::try_from(grid.spec().len).map_err(|_| {
DataFusionError::Execution("scalar grid length does not fit memory size".into())
})?;
let bytes = std::mem::size_of::<EvaluatedChunk>()
.checked_add(std::mem::size_of::<Float64Array>())
.and_then(|bytes| {
len.checked_mul(std::mem::size_of::<f64>())
.and_then(|values| bytes.checked_add(values))
})
.ok_or_else(|| {
DataFusionError::Execution("scalar allocation size overflow".into())
})?;
state.buffer.grow(bytes)?;
let chunk = scalar_chunk(grid, value)?;
state.buffer.metrics.record_completed_series(1);
state
.queued
.push_back((NativeChunk::Evaluated(chunk), bytes));
return state.pop_queued(evaluated_values);
}
self.root.pull(&mut self.inputs, inputs_finished)
}
@@ -2929,6 +2996,9 @@ impl NativeExecutionState {
fn close(&mut self) -> Result<()> {
let finished = self.root.finish_windows();
self.root.release();
if let Some((_, _, mut state)) = self.scalar_root.take() {
state.release();
}
// The slots are taken rather than only released: what a released slot still holds is its
// schema and the grid that schema is addressed on, and a caller that keeps the stopped
// executor would otherwise keep the input's schema and materialized timestamps alive past
@@ -2948,6 +3018,9 @@ impl NativeExecutionState {
/// vector and nothing left to take.
fn release(&mut self) {
self.root.release();
if let Some((_, _, mut state)) = self.scalar_root.take() {
state.release();
}
for mut slot in std::mem::take(&mut self.inputs) {
slot.release();
}
+143
View File
@@ -703,6 +703,149 @@ fn run(executor: &mut NativeExecutor) -> Vec<EvaluatedChunk> {
out
}
/// A scalar root answers its own value, once, on the grid it was bound to.
///
/// It reads nothing, so what it reports is not a series it was handed: one unlabelled chunk holding
/// one value per grid point and closing on that same chunk. Nothing above it exists, so the value's
/// field is the only field, and the chunk is addressed on the statement's grid rather than on one of
/// its own.
#[test]
fn scalar_root_emits_one_unlabelled_grid_chunk() {
let grid = grid(10, 5, 3);
let tree = NativeTree::try_new(scalar(2.5, Arc::clone(&grid))).unwrap();
let pool = pool();
let mut execution = executor(&tree, Arc::clone(&pool));
execution.end_of_input().unwrap();
let chunk = execution.next_chunk().unwrap().unwrap();
assert_eq!(
chunk.series.metric,
SeriesLabels::try_new(None, Vec::new()).unwrap(),
"a scalar carries no metric name and no labels"
);
assert_eq!(chunk.series.fields.len(), 1, "one value per grid point");
assert_eq!(sample_values(&chunk), vec![Some(2.5); 3]);
assert_eq!(chunk.series.time.len(), 3);
assert_eq!(
chunk.series.time.timestamps().unwrap().as_ref(),
grid.timestamps().unwrap().as_ref(),
"the chunk's positions are the statement's grid"
);
assert!(chunk.is_last, "the one chunk closes the value it reports");
assert!(
execution.next_chunk().unwrap().is_none(),
"a scalar owes one chunk and no second one"
);
assert_eq!(execution.state().reserved_bytes(), 0);
assert_eq!(pool.reserved(), 0);
}
/// The scalar's chunk is reserved before it is allocated, and its own node reports it.
///
/// The pool is asked first, so a low budget refuses the chunk instead of allocating it: the failure
/// leaves nothing held, and an execution stopped by it gives back everything it took. What the node
/// reports is the one batch and the values it produced, and no input at all, because it reads none.
#[test]
fn scalar_root_reserves_before_allocating_and_counts_its_output() {
let grid = grid(0, 1, 4);
let tree = NativeTree::try_new(scalar(2.0, Arc::clone(&grid))).unwrap();
let zero_pool = bounded_pool(0);
let mut rejected = executor(&tree, Arc::clone(&zero_pool));
rejected.end_of_input().unwrap();
let error = rejected.next_chunk().unwrap_err();
assert!(error.to_string().contains("memory"), "{error}");
assert_eq!(rejected.state().reserved_bytes(), 0);
assert_eq!(zero_pool.reserved(), 0);
// A stopped execution holds nothing either, and says so rather than answering again.
assert!(rejected.next_chunk().is_err());
let pool = pool();
let metrics = ExecutionPlanMetricsSet::new();
let state = NativeExecutionState::try_new(&tree, Arc::clone(&pool)).unwrap();
state.register_metrics(&metrics, 0);
let mut execution = NativeExecutor::new(state);
execution.end_of_input().unwrap();
let chunk = execution.next_chunk().unwrap().unwrap();
assert_eq!(sample_values(&chunk), vec![Some(2.0); 4]);
assert!(execution.next_chunk().unwrap().is_none());
assert_eq!(pool.reserved(), 0);
let peak = "native.p0.root.peak_reserved_bytes";
assert!(gauge(&metrics, peak) >= 4 * std::mem::size_of::<f64>());
assert_eq!(count(&metrics, "root", NodeMetric::OUTPUT_BATCHES), 1);
assert_eq!(count(&metrics, "root", NodeMetric::OUTPUT_VALUES), 4);
assert_eq!(
count(&metrics, "root", NodeMetric::EVALUATED_GRID_POINTS),
4
);
assert_eq!(count(&metrics, "root", NodeMetric::COMPLETED_SERIES), 1);
assert_eq!(count(&metrics, "root", NodeMetric::INPUT_BATCHES), 0);
assert_eq!(count(&metrics, "root", NodeMetric::INPUT_SAMPLES), 0);
}
/// A scalar can produce its value before the input ends.
///
/// Nothing arrives for it, so waiting would be waiting for a chunk no producer will send. Ending the
/// input afterwards changes nothing: the chunk was handed over once and the tree owes no second one.
#[test]
fn scalar_root_settles_before_the_input_ends() {
let tree = NativeTree::try_new(scalar(3.0, grid(0, 1, 3))).unwrap();
let mut execution = executor(&tree, pool());
assert_eq!(
sample_values(&execution.next_chunk().unwrap().unwrap()),
vec![Some(3.0); 3]
);
assert!(execution.next_chunk().unwrap().is_none());
execution.end_of_input().unwrap();
assert!(execution.next_chunk().unwrap().is_none());
assert_eq!(execution.state().reserved_bytes(), 0);
}
/// Stopped executors do not retain the scalar grid after handing off or rejecting the value.
#[test]
fn scalar_root_releases_grid_after_success_and_memory_failure() {
let pool = pool();
let (mut execution, weak_grid) = {
let grid = grid(0, 1, 3);
let tree = NativeTree::try_new(scalar(3.0, Arc::clone(&grid))).unwrap();
let weak = Arc::downgrade(&grid);
(executor(&tree, Arc::clone(&pool)), weak)
};
let chunk = execution.next_chunk().unwrap().unwrap();
assert!(weak_grid.upgrade().is_some());
drop(chunk);
execution.end_of_input().unwrap();
assert!(execution.next_chunk().unwrap().is_none());
assert!(weak_grid.upgrade().is_none());
let bounded = bounded_pool(0);
let (mut rejected, weak_grid) = {
let grid = grid(0, 1, 3);
let tree = NativeTree::try_new(scalar(3.0, Arc::clone(&grid))).unwrap();
let weak = Arc::downgrade(&grid);
(executor(&tree, Arc::clone(&bounded)), weak)
};
rejected.end_of_input().unwrap();
assert!(rejected.next_chunk().is_err());
assert_eq!(bounded.reserved(), 0);
assert!(weak_grid.upgrade().is_none());
}
/// Non-finite values and signed zero retain their bits rather than becoming missing samples.
#[test]
fn scalar_root_preserves_nan_negative_zero_and_infinity() {
for value in [f64::NAN, -0.0, f64::INFINITY, f64::NEG_INFINITY] {
let tree = NativeTree::try_new(scalar(value, grid(0, 1, 1))).unwrap();
let mut execution = executor(&tree, pool());
execution.end_of_input().unwrap();
let chunk = execution.next_chunk().unwrap().unwrap();
let actual = sample_values(&chunk)[0].expect("the point holds the constant");
assert_eq!(
actual.to_bits(),
value.to_bits(),
"the constant {value} is reported bit for bit"
);
}
}
fn sample_values(chunk: &EvaluatedChunk) -> Vec<Option<f64>> {
field_values(chunk, 0)
}
+1 -1
View File
@@ -141,7 +141,7 @@ pub struct BoundInput {
pub ordering: SeriesOrdering,
}
/// A constant scalar bound for broadcast.
/// A constant scalar bound for broadcast or a statement root.
///
/// A scalar that varies per grid point is the same [`NativeType::Scalar`] as this constant: what
/// keeps a binary operation from label-matching it is its type, not its constness. This binding
+39
View File
@@ -14,6 +14,7 @@
use std::sync::Arc;
use datafusion::common::DFSchema;
use datatypes::series::SeriesOrdering;
use datatypes::series::samples::{FieldSpec, SeriesSchema};
use datatypes::series::time::{EvalGrid, GridSpec};
@@ -23,6 +24,7 @@ use super::{
BoundVectorOp, BoundWindow, Grouping, MapOp, NativeExpr, NativeNode, NativeTree, NativeType,
reads_across_series,
};
use crate::extension_plan::{FusedSeries, FusedSeriesBinding};
use crate::map::MathOp;
use crate::range_eval::{RangeFunction, RangeWindow};
use crate::vector_match::{BinaryMatching, BinaryOp, Cardinality, FillValues, MatchingLabels};
@@ -1302,3 +1304,40 @@ fn a_vector_operation_cannot_consume_raw_samples() {
let error = node.validate().unwrap_err();
assert!(error.to_string().contains("an evaluated vector"), "{error}");
}
/// A node that reports samples while holding no input node is refused where the node is built.
///
/// The tree is constructed directly here — a child module of `native::plan` may — because the node
/// is one the public constructors decline: a scalar root is the only zero-input shape a fused node
/// accepts, and samples without a source would be an empty vector reported as an answer. Every
/// public constructor therefore stays a checked one.
#[test]
fn a_samples_root_without_an_input_is_refused() {
let statement_grid = grid(0, 60_000, 4);
let tree = NativeTree {
root: NativeNode {
expr: NativeExpr::Scalar(BoundScalar { value: 1.0 }),
output: evaluated(Arc::new([]), Arc::clone(&statement_grid)),
},
};
let binding = FusedSeriesBinding {
grid: statement_grid,
time_index: "time".to_string(),
tags: vec![],
metric_name: None,
};
let error = FusedSeries::try_new(
Arc::from("1"),
tree,
binding,
Vec::new(),
Arc::new(DFSchema::empty()),
)
.expect_err("a samples root reads no source while reporting samples");
assert!(
error.to_string().contains("constant scalar"),
"the refusal must name the shape a zero-child tree has to be: {error}"
);
}
+21 -4
View File
@@ -109,8 +109,8 @@
//!
//! Vector matching is bound with each selector's own input, including the labels and cardinality
//! written on a vector–vector operation. A scalar has no input of its own: it is bound next to the
//! vector that gives it something to broadcast over, while a statement whose value is only a scalar
//! has nothing to read and is refused.
//! vector that gives it something to broadcast over, while a statement whose value is only a
//! constant is bound by [`compile_statement`] as that constant on the statement's grid.
//!
//! An aggregate is bound as [`AggregateStage::Complete`], which is a claim about the whole execution
//! rather than about the node: it says that every contribution to every group is in this execution's
@@ -289,7 +289,21 @@ pub fn compile(
Ok(compiled.tree)
}
/// Compiles a statement and returns a binding record for each selector occurrence.
/// Compiles a constant statement to a scalar on the statement's grid, reading no input.
///
/// A value that depends on data or on the evaluation time is refused, which the same fold
/// [`compile_expr`] uses for a constant operand decides ([`constant_value`]).
pub fn compile_statement(stmt: &EvalStmt) -> Result<NativeTree> {
let value = constant_value(&stmt.expr)
.ok_or_else(|| not_implemented(&format!("the expression `{}`", stmt.expr)))?;
let grid = statement_grid(stmt)?;
NativeTree::try_new(NativeNode {
expr: NativeExpr::Scalar(BoundScalar { value }),
output: NativeType::Scalar(grid),
})
}
/// Compiles `stmt` into a tree and returns a binding record for each selector occurrence.
///
/// `bindings` is called once per selector with its requirements. The resulting source indices are
/// occurrence numbers in compiler traversal order; the caller maps them to scan children.
@@ -305,6 +319,8 @@ pub fn compile_selectors(
series may not interleave",
));
}
// A tree with selector inputs reports evaluated vector samples. A constant root has no input
// and is bound separately by [`compile_statement`].
if stmt.expr.value_type() != ValueType::Vector {
return Err(not_implemented(&format!(
"the expression `{}`, which is a {} where a tree reports evaluated samples",
@@ -1808,7 +1824,8 @@ fn refuses_modifier(modifier: Option<&BinModifier>) -> bool {
/// semantics for `%`, `^` and `atan2` live, the last two through `go_math`, so defining them again
/// here would be a second answer for the two to disagree over. An operator with no
/// [`ArithmeticOp`] — a comparison, `and`, `or`, `unless` — is not arithmetic and does not fold.
fn constant_value(expr: &PromExpr) -> Option<f64> {
/// Visible to the planner, which asks whether a statement's value is a constant before binding it.
pub(crate) fn constant_value(expr: &PromExpr) -> Option<f64> {
match expr {
PromExpr::NumberLiteral(NumberLiteral { val }) => Some(*val),
PromExpr::Paren(paren) => constant_value(&paren.expr),
+37 -1
View File
@@ -38,7 +38,8 @@ use promql_parser::parser::{
};
use super::{
CompiledInput, SelectorRequirement, SelectorTiming, compile, compile_selectors, validate_inputs,
CompiledInput, SelectorRequirement, SelectorTiming, compile, compile_selectors,
compile_statement, validate_inputs,
};
/// Whether a matching names its labels with `on` (`true`) or `ignoring` (`false`), and which.
@@ -1865,6 +1866,41 @@ fn a_statement_with_no_vector_is_refused() {
}
}
/// A constant statement compiles to the constant on the statement's grid, and it reads nothing.
///
/// The vector entry above refuses it — a tree over that entry reports evaluated samples — so the
/// statement entry is the one that binds it, and the grid it reports on is the statement's own.
#[test]
fn a_constant_statement_is_a_scalar_on_the_statement_grid_without_input() {
for (query, value) in [("1 + 2", 3.0), ("-1", -1.0)] {
let stmt = eval_stmt(query);
let tree = compile_statement(&stmt)
.unwrap_or_else(|error| panic!("`{query}` was refused: {error}"));
// The root is the number the statement means, on the statement's own grid: 100 seconds in
// 5-second steps is 21 points, and no point is the constant's to choose.
assert_eq!(Some(value), constant(tree.root()), "query: {query}");
assert_eq!((0, 5_000, 21), scalar_grid(tree.root()), "query: {query}");
}
}
/// A statement whose value comes from the data or from the evaluation time has no constant to bind,
/// so the statement entry refuses it rather than compiling a tree with nothing to read.
#[test]
fn a_statement_that_is_not_constant_has_no_statement_compilation() {
for query in ["time()", "time() + 1", "vector(1)", "x"] {
let error = compile_statement(&eval_stmt(query))
.expect_err(&format!("`{query}` compiled, and it should not have"));
assert!(
matches!(error, DataFusionError::NotImplemented(_)),
"`{query}` did not report NotImplemented: {error}"
);
assert!(
error.to_string().contains(&format!("`{query}`")),
"`{query}` did not name the expression it found: {error}"
);
}
}
/// A vector-matching modifier has nothing to match when one operand is a constant, and the tree's
/// matching has no field for a fill value. Both are refused rather than dropped: dropping one would
/// compile a query into an operation other than the one it wrote. `bool` is not a matching modifier
+47 -6
View File
@@ -29,6 +29,8 @@
//! built to the shape the existing unary pipeline produces — the time index, then the series
//! fields, then the tags — so a node planned here can be consumed by the same code that consumes a
//! `SeriesNormalize` output.
//!
//! A constant statement is planned with no scan: one node, no child, the time index and value.
use std::sync::Arc;
use std::time::{Duration, UNIX_EPOCH};
@@ -56,8 +58,10 @@ use snafu::ResultExt;
use store_api::metric_engine_consts::{DATA_SCHEMA_TABLE_ID_COLUMN_NAME, METRIC_ENGINE_NAME};
use crate::promql::error::{DataFusionPlanningSnafu, Result};
use crate::promql::native_compile::{compile_selectors, statement_grid};
use crate::promql::planner::PromPlanner;
use crate::promql::native_compile::{
compile_selectors, compile_statement, constant_value, statement_grid,
};
use crate::promql::planner::{DEFAULT_FIELD_COLUMN, DEFAULT_TIME_INDEX_COLUMN, PromPlanner};
use crate::query_engine::QueryEngineState;
/// The query-context key that turns the native fused-series route on for one query.
@@ -141,10 +145,7 @@ impl PromPlanner {
}
let mut selectors = Vec::new();
if !collect_selectors(prom_expr, &mut selectors)
|| selectors.is_empty()
|| selectors.len() > 2
{
if !collect_selectors(prom_expr, &mut selectors) || selectors.len() > 2 {
return Ok(None);
}
// Preserve the original single-selector admission allowlist. Broader binary syntax is only
@@ -158,6 +159,39 @@ impl PromPlanner {
let Ok(grid) = statement_grid(&stmt) else {
return Ok(None);
};
// No selector is not proof of a constant: `time()` and other data-free functions are
// unsupported here, so the existing fold is asked before a zero-child node is bound.
if selectors.is_empty() {
if constant_value(prom_expr).is_none() {
return Ok(None);
}
let tree = match compile_statement(&stmt) {
Ok(tree) => tree,
Err(DataFusionError::NotImplemented(_)) => return Ok(None),
Err(error) => return Err(error).context(DataFusionPlanningSnafu),
};
// A constant has no scan: no metric, no tags, and the value under the name the existing
// path gives a bare literal.
let time_index = DEFAULT_TIME_INDEX_COLUMN.to_string();
let value = DEFAULT_FIELD_COLUMN.to_string();
let output_schema = fused_output_schema(&[value], &[], &time_index)?;
let node = FusedSeries::try_new(
Arc::from(prom_expr.to_string()),
tree,
FusedSeriesBinding {
grid,
time_index,
tags: Vec::new(),
metric_name: None,
},
Vec::new(),
output_schema,
)
.context(DataFusionPlanningSnafu)?;
return Ok(Some(LogicalPlan::Extension(Extension {
node: Arc::new(node),
})));
}
let original_context = self.ctx.clone();
let preparation = async {
let mut prepared: Vec<PreparedInput> = Vec::new();
@@ -742,6 +776,13 @@ fn admitted_selector(expr: &PromExpr) -> Option<&VectorSelector> {
{
admitted_selector(&call.args.args[0])
}
PromExpr::Unary(unary) => admitted_selector(&unary.expr),
PromExpr::Binary(binary) if constant_value(&binary.lhs).is_some() => {
admitted_selector(&binary.rhs)
}
PromExpr::Binary(binary) if constant_value(&binary.rhs).is_some() => {
admitted_selector(&binary.lhs)
}
_ => None,
}
}
+33
View File
@@ -1859,6 +1859,39 @@ fn find_fused_series(plan: &LogicalPlan) -> Option<&FusedSeries> {
plan.inputs().into_iter().find_map(find_fused_series)
}
/// Literal roots need no raw scan, while a literal beside a selector broadcasts over that input.
#[tokio::test]
async fn native_fused_supports_constant_roots_and_selector_broadcasts() {
for (query, value) in [("1 + 2", 3.0), ("-1", -1.0)] {
let plan = build_native_fused_plan(query, true).await;
let fused = find_fused_series(&plan).expect("constant root uses native route");
assert!(
fused.children().is_empty(),
"{query}: {:?}",
fused.children()
);
let NativeExpr::Scalar(scalar) = &fused.tree().root().expr else {
panic!("{query}: {:?}", fused.tree().root().expr);
};
assert_eq!(value, scalar.value, "{query}");
}
for query in [
"some_metric * 100",
"100 / some_metric",
"-some_metric",
"rate(some_metric[5m]) * 100",
] {
let plan = build_native_fused_plan(query, true).await;
let fused = find_fused_series(&plan).expect("selector expression uses native route");
assert_eq!(1, fused.children().len(), "{query}");
assert!(
matches!(fused.children()[0], LogicalPlan::TableScan(_)),
"{query}"
);
}
}
/// The flag on and a shape the compiler accepts: the statement plans to one native node.
#[tokio::test]
async fn native_fused_rate_plans_to_a_fused_series_node() {