Files
grafana/pkg/expr/reader.go
Sam Jewell 7a3415148e SQL Expressions: Add cell-limit for input dataframes (#101700)
* expr: Add row limit to SQL expressions

Adds a configurable row limit to SQL expressions to prevent memory issues with large
result sets. The limit is configured via the `sql_expression_row_limit` setting in
the `[expressions]` section of grafana.ini, with a default of 100,000 rows.

The limit is enforced by checking the total number of rows across all input tables
before executing the SQL query. If the total exceeds the limit, the query fails
with an error message indicating the limit was exceeded.

* revert addition of newline

* Switch to table-driven tests

* Remove single-frame test-cases.

We only need to test for the multi frame case. Single frame is a subset
of the multi-frame case

* Add helper function

Simplify the way tests are set up and written

* Support convention, that limit: 0 is no limit

* Set the row-limit in one place only

* Update default limit to 20k rows

As per some discussion here:
https://raintank-corp.slack.com/archives/C071A5XCFST/p1741611647001369?thread_ts=1740047619.804869&cid=C071A5XCFST

* Test row-limit is applied from config

Make sure we protect this from regressions

This is perhaps a brittle test, somewhat coupled to the code here. But
it's good enough to prevent regressions at least.

* Add public documentation for the limit

* Limit total number of cells instead of rows

* Use named-return for totalRows

As @kylebrandt requested during review of #101700

* Leave DF cells as zero values during limits tests

When testing the cell limit we don't interact with the cell values at
all, so we leave them at their zero values both to speed up tests, and
to simplify and clarify that their values aren't used.

* Set SQLCmd limit at object creation - don't mutate

* Test that SQL node receives limit when built

And that it receives it from the Grafana config

* Improve TODO message for new Expression Parser

* Fix failing test by always creating config on the Service
2025-03-11 17:14:33 +00:00

203 lines
5.7 KiB
Go

package expr
import (
"fmt"
"strings"
"github.com/grafana/grafana-plugin-sdk-go/backend/gtime"
"github.com/grafana/grafana-plugin-sdk-go/data/utils/jsoniter"
data "github.com/grafana/grafana-plugin-sdk-go/experimental/apis/data/v0alpha1"
"github.com/grafana/grafana/pkg/expr/classic"
"github.com/grafana/grafana/pkg/expr/mathexp"
"github.com/grafana/grafana/pkg/services/featuremgmt"
)
// Once we are comfortable with the parsing logic, this struct will
// be merged/replace the existing Query struct in grafana/pkg/expr/transform.go
type ExpressionQuery struct {
GraphID int64 `json:"id,omitempty"`
RefID string `json:"refId"`
QueryType QueryType `json:"type"`
// The typed query parameters
Properties any `json:"properties"`
// Hidden in debug JSON
Command Command `json:"-"`
}
// ID is used to identify nodes in the directed graph
func (q ExpressionQuery) ID() int64 {
return q.GraphID
}
type ExpressionQueryReader struct {
features featuremgmt.FeatureToggles
}
func NewExpressionQueryReader(features featuremgmt.FeatureToggles) *ExpressionQueryReader {
return &ExpressionQueryReader{
features: features,
}
}
// nolint:gocyclo
func (h *ExpressionQueryReader) ReadQuery(
// Properties that have been parsed off the same node
common data.DataQuery,
// An iterator with context for the full node (include common values)
iter *jsoniter.Iterator,
) (eq ExpressionQuery, err error) {
referenceVar := ""
eq.RefID = common.RefID
eq.QueryType = QueryType(common.GetString("type"))
if eq.QueryType == "" {
return eq, fmt.Errorf("missing type")
}
switch eq.QueryType {
case QueryTypeMath:
q := &MathQuery{}
err = iter.ReadVal(q)
if err == nil {
eq.Command, err = NewMathCommand(common.RefID, q.Expression)
eq.Properties = q
}
case QueryTypeReduce:
var mapper mathexp.ReduceMapper = nil
q := &ReduceQuery{}
err = iter.ReadVal(q)
if err == nil {
referenceVar, err = getReferenceVar(q.Expression, common.RefID)
eq.Properties = q
}
if err == nil && q.Settings != nil {
switch q.Settings.Mode {
case ReduceModeStrict:
mapper = nil
case ReduceModeDrop:
mapper = mathexp.DropNonNumber{}
case ReduceModeReplace:
if q.Settings.ReplaceWithValue == nil {
err = fmt.Errorf("setting replaceWithValue must be specified when mode is '%s'", q.Settings.Mode)
}
mapper = mathexp.ReplaceNonNumberWithValue{Value: *q.Settings.ReplaceWithValue}
default:
err = fmt.Errorf("unsupported reduce mode")
}
}
if err == nil {
eq.Properties = q
eq.Command, err = NewReduceCommand(common.RefID,
q.Reducer, referenceVar, mapper)
}
case QueryTypeResample:
q := &ResampleQuery{}
err = iter.ReadVal(q)
if err == nil && common.TimeRange == nil {
err = fmt.Errorf("missing time range in query")
}
if err == nil {
referenceVar, err = getReferenceVar(q.Expression, common.RefID)
}
if err == nil {
tr := gtime.NewTimeRange(common.TimeRange.From, common.TimeRange.To)
eq.Properties = q
eq.Command, err = NewResampleCommand(common.RefID,
q.Window,
referenceVar,
q.Downsampler,
q.Upsampler,
AbsoluteTimeRange{
From: tr.GetFromAsTimeUTC(),
To: tr.GetToAsTimeUTC(),
},
)
}
case QueryTypeClassic:
q := &ClassicQuery{}
err = iter.ReadVal(q)
if err == nil {
eq.Properties = q
eq.Command, err = classic.NewConditionCmd(common.RefID, q.Conditions)
}
case QueryTypeSQL:
enabled := enableSqlExpressions(h)
if !enabled {
return eq, fmt.Errorf("sqlExpressions is not implemented")
}
q := &SQLExpression{}
err = iter.ReadVal(q)
if err == nil {
eq.Properties = q
// TODO: Cascade limit from Grafana config in this (new Expression Parser) branch of the code
cellLimit := 0 // zero means no limit
eq.Command, err = NewSQLCommand(common.RefID, q.Expression, int64(cellLimit))
}
case QueryTypeThreshold:
q := &ThresholdQuery{}
err = iter.ReadVal(q)
if err == nil {
referenceVar, err = getReferenceVar(q.Expression, common.RefID)
}
if err == nil {
// we only support one condition for now, we might want to turn this in to "OR" expressions later
if len(q.Conditions) != 1 {
return eq, fmt.Errorf("threshold expression requires exactly one condition")
}
firstCondition := q.Conditions[0]
threshold, err := NewThresholdCommand(common.RefID, referenceVar, firstCondition.Evaluator.Type, firstCondition.Evaluator.Params)
if err != nil {
return eq, fmt.Errorf("invalid condition: %w", err)
}
eq.Command = threshold
eq.Properties = q
if firstCondition.UnloadEvaluator != nil && h.features.IsEnabledGlobally(featuremgmt.FlagRecoveryThreshold) {
unloading, err := NewThresholdCommand(common.RefID, referenceVar, firstCondition.UnloadEvaluator.Type, firstCondition.UnloadEvaluator.Params)
unloading.Invert = true
if err != nil {
return eq, fmt.Errorf("invalid unloadCondition: %w", err)
}
var d Fingerprints
if firstCondition.LoadedDimensions != nil {
d, err = FingerprintsFromFrame(firstCondition.LoadedDimensions)
if err != nil {
return eq, fmt.Errorf("failed to parse loaded dimensions: %w", err)
}
}
eq.Command, err = NewHysteresisCommand(common.RefID, referenceVar, *threshold, *unloading, d)
if err != nil {
return eq, err
}
}
}
default:
err = fmt.Errorf("unknown query type (%s)", common.QueryType)
}
return eq, err
}
func getReferenceVar(exp string, refId string) (string, error) {
exp = strings.TrimPrefix(exp, "$")
if exp == "" {
return "", fmt.Errorf("no variable specified to reference for refId %v", refId)
}
return exp, nil
}
func enableSqlExpressions(h *ExpressionQueryReader) bool {
enabled := !h.features.IsEnabledGlobally(featuremgmt.FlagSqlExpressions)
if enabled {
return false
}
return false
}