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

Loki: Fix parser hint for extracted labels which collide with stream labels #3380

Merged
merged 3 commits into from
Feb 25, 2021
Merged

Loki: Fix parser hint for extracted labels which collide with stream labels #3380

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ebfbf27
add test for issue with hints and extracted labels
slim-bean Feb 24, 2021
51de82a
one possible solution
slim-bean Feb 24, 2021
3847305
instead of replacing the label with the _extracted suffix removed, ju…
slim-bean Feb 24, 2021
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
16 changes: 16 additions & 0 deletions pkg/logql/log/parser_hints.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,22 @@ func (p *parserHint) NoLabels() bool {

// newParserHint creates a new parser hint using the list of labels that are seen and required in a query.
func newParserHint(requiredLabelNames, groups []string, without, noLabels bool, metricLabelName string) *parserHint {
// If a parsed label collides with a stream label we add the `_extracted` suffix to it, however hints
// are used by the parsers before we know they will collide with a stream label and hence before the
// _extracted suffix is added. Therefore we must strip the _extracted suffix from any required labels
// that were parsed from somewhere in the query, say in a filter or an aggregation clause.
// Because it's possible for a valid json or logfmt key to already end with _extracted, we'll just
// leave the existing entry ending with _extracted but also add a version with the suffix removed.
extractedLabels := []string{}
for _, l := range requiredLabelNames {
if strings.HasSuffix(l, "_extracted") {
extractedLabels = append(extractedLabels, strings.TrimSuffix(l, "_extracted"))
}
}
if len(extractedLabels) > 0 {
requiredLabelNames = append(requiredLabelNames, extractedLabels...)
}

if len(groups) > 0 {
requiredLabelNames = append(requiredLabelNames, groups...)
}
Expand Down
26 changes: 17 additions & 9 deletions pkg/logql/log/parser_hints_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ var (
"remote_user": "foo",
"upstream_addr": "10.0.0.1:80",
"protocol": "HTTP/2.0",
"cluster": "us-east-west",
"request": {
"time": "30.001",
"method": "POST",
Expand All @@ -32,7 +33,7 @@ var (
)

func Test_ParserHints(t *testing.T) {
lbs := labels.Labels{{Name: "app", Value: "nginx"}}
lbs := labels.Labels{{Name: "app", Value: "nginx"}, {Name: "cluster", Value: "us-central-west"}}

t.Parallel()
for _, tt := range []struct {
Expand All @@ -47,14 +48,14 @@ func Test_ParserHints(t *testing.T) {
jsonLine,
true,
1.0,
`{app="nginx", protocol="HTTP/2.0", remote_user="foo", request_host="foo.grafana.net", request_method="POST", request_size="101", request_time="30.001", request_uri="/rpc/v2/stage", response_latency_seconds="30.001", response_status="204", upstream_addr="10.0.0.1:80"}`,
`{app="nginx", cluster="us-central-west", cluster_extracted="us-east-west", protocol="HTTP/2.0", remote_user="foo", request_host="foo.grafana.net", request_method="POST", request_size="101", request_time="30.001", request_uri="/rpc/v2/stage", response_latency_seconds="30.001", response_status="204", upstream_addr="10.0.0.1:80"}`,
},
{
`sum without (request_host,app) (rate({app="nginx"} | json | __error__="" | response_status = 204 [1m]))`,
`sum without (request_host,app,cluster) (rate({app="nginx"} | json | __error__="" | response_status = 204 [1m]))`,
jsonLine,
true,
1.0,
`{protocol="HTTP/2.0", remote_user="foo", request_method="POST", request_size="101", request_time="30.001", request_uri="/rpc/v2/stage", response_latency_seconds="30.001", response_status="204", upstream_addr="10.0.0.1:80"}`,
`{cluster_extracted="us-east-west", protocol="HTTP/2.0", remote_user="foo", request_method="POST", request_size="101", request_time="30.001", request_uri="/rpc/v2/stage", response_latency_seconds="30.001", response_status="204", upstream_addr="10.0.0.1:80"}`,
},
{
`sum by (request_host,app) (rate({app="nginx"} | json | __error__="" | response_status = 204 [1m]))`,
Expand Down Expand Up @@ -103,14 +104,14 @@ func Test_ParserHints(t *testing.T) {
jsonLine,
true,
30.001,
`{app="nginx", protocol="HTTP/2.0", remote_user="foo", request_host="foo.grafana.net", request_method="POST", request_size="101", request_time="30.001", request_uri="/rpc/v2/stage", response_status="204", upstream_addr="10.0.0.1:80"}`,
`{app="nginx", cluster="us-central-west", cluster_extracted="us-east-west", protocol="HTTP/2.0", remote_user="foo", request_host="foo.grafana.net", request_method="POST", request_size="101", request_time="30.001", request_uri="/rpc/v2/stage", response_status="204", upstream_addr="10.0.0.1:80"}`,
},
{
`sum without (request_host,app)(rate({app="nginx"} | json | response_status = 204 | unwrap response_latency_seconds [1m]))`,
`sum without (request_host,app,cluster)(rate({app="nginx"} | json | response_status = 204 | unwrap response_latency_seconds [1m]))`,
jsonLine,
true,
30.001,
`{protocol="HTTP/2.0", remote_user="foo", request_method="POST", request_size="101", request_time="30.001", request_uri="/rpc/v2/stage", response_status="204", upstream_addr="10.0.0.1:80"}`,
`{cluster_extracted="us-east-west", protocol="HTTP/2.0", remote_user="foo", request_method="POST", request_size="101", request_time="30.001", request_uri="/rpc/v2/stage", response_status="204", upstream_addr="10.0.0.1:80"}`,
},
{
`sum(rate({app="nginx"} | logfmt | org_id=3677 | unwrap Ingester_TotalReached[1m]))`,
Expand All @@ -131,10 +132,10 @@ func Test_ParserHints(t *testing.T) {
logfmtLine,
true,
15.0,
`{Ingester_TotalBatches="0", Ingester_TotalChunksMatched="0", app="nginx", caller="spanlogger.go:79", org_id="3677", traceID="2e5c7234b8640997", ts="2021-02-02T14:35:05.983992774Z"}`,
`{Ingester_TotalBatches="0", Ingester_TotalChunksMatched="0", app="nginx", caller="spanlogger.go:79", cluster="us-central-west", org_id="3677", traceID="2e5c7234b8640997", ts="2021-02-02T14:35:05.983992774Z"}`,
},
{
`sum without (org_id,app)(rate({app="nginx"} | logfmt | org_id=3677 | unwrap Ingester_TotalReached[1m]))`,
`sum without (org_id,app,cluster)(rate({app="nginx"} | logfmt | org_id=3677 | unwrap Ingester_TotalReached[1m]))`,
logfmtLine,
true,
15.0,
Expand Down Expand Up @@ -175,6 +176,13 @@ func Test_ParserHints(t *testing.T) {
1.0,
`{}`,
},
{
`sum by (cluster_extracted)(count_over_time({app="nginx"} | json | cluster_extracted="us-east-west" [1m]))`,
jsonLine,
true,
1.0,
`{cluster_extracted="us-east-west"}`,
},
} {
tt := tt
t.Run(tt.expr, func(t *testing.T) {
Expand Down