Files
grafana/pkg/expr/graph_test.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

296 lines
6.2 KiB
Go

package expr
import (
"encoding/json"
"testing"
"github.com/stretchr/testify/require"
"github.com/grafana/grafana/pkg/services/datasources"
"github.com/grafana/grafana/pkg/services/featuremgmt"
"github.com/grafana/grafana/pkg/setting"
)
func TestServicebuildPipeLine(t *testing.T) {
var tests = []struct {
name string
req *Request
expectedOrder []string
expectErrContains string
}{
{
name: "simple: a requires b",
req: &Request{
Queries: []Query{
{
RefID: "A",
DataSource: dataSourceModel(),
JSON: json.RawMessage(`{
"expression": "B",
"reducer": "mean",
"type": "reduce"
}`),
},
{
RefID: "B",
DataSource: &datasources.DataSource{
UID: "Fake",
},
TimeRange: AbsoluteTimeRange{},
},
},
},
expectedOrder: []string{"B", "A"},
},
{
name: "cycle will error",
req: &Request{
Queries: []Query{
{
RefID: "A",
DataSource: dataSourceModel(),
JSON: json.RawMessage(`{
"expression": "$B",
"type": "math"
}`),
},
{
RefID: "B",
DataSource: dataSourceModel(),
JSON: json.RawMessage(`{
"expression": "$A",
"type": "math"
}`),
},
},
},
expectErrContains: "cyclic components",
},
{
name: "self reference will error",
req: &Request{
Queries: []Query{
{
RefID: "A",
DataSource: dataSourceModel(),
JSON: json.RawMessage(`{
"expression": "$A",
"type": "math"
}`),
},
},
},
expectErrContains: "expression 'A' cannot reference itself. Must be query or another expression",
},
{
name: "missing dependency will error",
req: &Request{
Queries: []Query{
{
RefID: "A",
DataSource: dataSourceModel(),
JSON: json.RawMessage(`{
"expression": "$B",
"type": "math"
}`),
},
},
},
expectErrContains: "find dependent",
},
{
name: "classic can not take input from another expression",
req: &Request{
Queries: []Query{
{
RefID: "A",
DataSource: dataSourceModel(),
JSON: json.RawMessage(`{
"type": "classic_conditions",
"conditions": [
{
"evaluator": {
"params": [
2,
3
],
"type": "within_range"
},
"operator": {
"type": "or"
},
"query": {
"params": [
"B"
]
},
"reducer": {
"params": [],
"type": "diff"
},
"type": "query"
}
]
}`),
},
{
RefID: "B",
DataSource: dataSourceModel(),
JSON: json.RawMessage(`{
"expression": "C",
"reducer": "mean",
"type": "reduce"
}`),
},
{
RefID: "C",
DataSource: &datasources.DataSource{
UID: "Fake",
},
TimeRange: AbsoluteTimeRange{},
},
},
},
expectErrContains: "only data source queries may be inputs to a classic condition",
},
{
name: "classic can not output to another expression",
req: &Request{
Queries: []Query{
{
RefID: "A",
DataSource: dataSourceModel(),
JSON: json.RawMessage(`{
"type": "classic_conditions",
"conditions": [
{
"evaluator": {
"params": [
2,
3
],
"type": "within_range"
},
"operator": {
"type": "or"
},
"query": {
"params": [
"C"
]
},
"reducer": {
"params": [],
"type": "diff"
},
"type": "query"
}
]
}`),
},
{
RefID: "B",
DataSource: dataSourceModel(),
JSON: json.RawMessage(`{
"expression": "A",
"reducer": "mean",
"type": "reduce"
}`),
},
{
RefID: "C",
DataSource: &datasources.DataSource{
UID: "Fake",
},
TimeRange: AbsoluteTimeRange{},
},
},
},
expectErrContains: "classic conditions may not be the input for other expressions",
},
{
name: "Queries with new datasource ref object",
req: &Request{
Queries: []Query{
{
RefID: "A",
DataSource: dataSourceModel(),
JSON: json.RawMessage(`{
"expression": "B",
"reducer": "mean",
"type": "reduce"
}`),
},
{
RefID: "B",
DataSource: &datasources.DataSource{
UID: "Fake",
},
TimeRange: AbsoluteTimeRange{},
},
},
},
expectedOrder: []string{"B", "A"},
},
}
s := Service{
features: featuremgmt.WithFeatures(featuremgmt.FlagExpressionParser),
cfg: setting.NewCfg(),
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
nodes, err := s.buildPipeline(tt.req)
if tt.expectErrContains != "" {
require.Error(t, err)
require.Contains(t, err.Error(), tt.expectErrContains)
} else {
require.NoError(t, err)
require.Equal(t, tt.expectedOrder, getRefIDOrder(nodes))
}
})
}
}
func TestGetCommandsFromPipeline(t *testing.T) {
pipeline := DataPipeline{
&MLNode{},
&DSNode{},
&CMDNode{
baseNode: baseNode{},
CMDType: 0,
Command: &ReduceCommand{},
},
&CMDNode{
baseNode: baseNode{},
CMDType: 0,
Command: &ReduceCommand{},
},
&CMDNode{
baseNode: baseNode{},
CMDType: 0,
Command: &HysteresisCommand{},
},
}
t.Run("should find command that exists", func(t *testing.T) {
cmds := GetCommandsFromPipeline[*HysteresisCommand](pipeline)
require.Len(t, cmds, 1)
require.Equal(t, pipeline[4].(*CMDNode).Command, cmds[0])
})
t.Run("should find all commands that exist", func(t *testing.T) {
cmds := GetCommandsFromPipeline[*ReduceCommand](pipeline)
require.Len(t, cmds, 2)
})
t.Run("should not find all command that does not exist", func(t *testing.T) {
cmds := GetCommandsFromPipeline[*MathCommand](pipeline)
require.Len(t, cmds, 0)
})
}
func getRefIDOrder(nodes []Node) []string {
ids := make([]string, 0, len(nodes))
for _, n := range nodes {
ids = append(ids, n.RefID())
}
return ids
}