feat: use xxhash for error grouping key (#15211)

* feat: use xxhash for error grouping key

bump apm-data and replace md5 with xxhash

* lint: regenerate notice

NOTICE.txt

@@ -393,11 +393,11 @@ these terms.
 
 --------------------------------------------------------------------------------
 Dependency : github.com/elastic/apm-data
-Version: v1.15.0
+Version: v1.16.0
 Licence type (autodetected): Apache-2.0
 --------------------------------------------------------------------------------
 
-Contents of probable licence file $GOMODCACHE/github.com/elastic/apm-data@v1.15.0/LICENSE:
+Contents of probable licence file $GOMODCACHE/github.com/elastic/apm-data@v1.16.0/LICENSE:
 
                                  Apache License
                            Version 2.0, January 2004

go.mod

@@ -8,7 +8,7 @@ require (
 	github.com/dgraph-io/badger/v2 v2.2007.4
 	github.com/dustin/go-humanize v1.0.1
 	github.com/elastic/apm-aggregation v1.2.0
-	github.com/elastic/apm-data v1.15.0
+	github.com/elastic/apm-data v1.16.0
 	github.com/elastic/beats/v7 v7.0.0-alpha2.0.20241231140711-7806f1a2cb26
 	github.com/elastic/elastic-agent-client/v7 v7.17.0
 	github.com/elastic/elastic-agent-libs v0.18.1

go.sum

@@ -126,8 +126,8 @@ github.com/ebitengine/purego v0.8.0 h1:JbqvnEzRvPpxhCJzJJ2y0RbiZ8nyjccVUrSM3q+Gv
 github.com/ebitengine/purego v0.8.0/go.mod h1:iIjxzd6CiRiOG0UyXP+V1+jWqUXVjPKLAI0mRfJZTmQ=
 github.com/elastic/apm-aggregation v1.2.0 h1:UndqG3ccBTjyxTqHujBVjcbVLb9qG1clxRcrp9JRelI=
 github.com/elastic/apm-aggregation v1.2.0/go.mod h1:YllYwPYVV27pbuPfjRtQAKo6eSSrh13PZr38RKYd810=
-github.com/elastic/apm-data v1.15.0 h1:19qq8+OC+eyylUMtd2TrW1YVGrOgXb4d2OJQoqfmqow=
-github.com/elastic/apm-data v1.15.0/go.mod h1:PAkbYNARxvd4nhR+HjCskGv/ev30zZi7jglf8EmWtXc=
+github.com/elastic/apm-data v1.16.0 h1:LkJFoNkadIyqXNo3EMm98J38j9HWDMWUe6F74GaXtJ4=
+github.com/elastic/apm-data v1.16.0/go.mod h1:ST2P1yshhN2U3IbBYyn+Ni3VOFTifavNzMfh7E9zLHY=
 github.com/elastic/beats/v7 v7.0.0-alpha2.0.20241231140711-7806f1a2cb26 h1:qyI4AIRfdnTwesqHN9KYdbGpcJ4m4lIKlR+f8zbKIO0=
 github.com/elastic/beats/v7 v7.0.0-alpha2.0.20241231140711-7806f1a2cb26/go.mod h1:CgYrkUfXIWj/lcPc5ipnO0/2OEx4GmstkLzyUHilme8=
 github.com/elastic/elastic-agent-autodiscover v0.9.0 h1:+iWIKh0u3e8I+CJa3FfWe9h0JojNasPgYIA47gpuuns=

internal/beater/beater.go

@@ -22,13 +22,15 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"hash"
 	"net"
 	"net/http"
 	"os"
 	"runtime"
 	"strconv"
 	"time"
 
+	"github.com/cespare/xxhash/v2"
 	"github.com/dustin/go-humanize"
 	"go.elastic.co/apm/module/apmgrpc/v2"
 	"go.elastic.co/apm/module/apmotel/v2"
@@ -471,7 +473,11 @@ func (s *Runner) Run(ctx context.Context) error {
 		// aggregation, sampling, and indexing.
 		modelprocessor.SetHostHostname{},
 		modelprocessor.SetServiceNodeName{},
-		modelprocessor.SetGroupingKey{},
+		modelprocessor.SetGroupingKey{
+			NewHash: func() hash.Hash {
+				return xxhash.New()
+			},
+		},
 		modelprocessor.SetErrorMessage{},
 	}
 	if s.config.DefaultServiceEnvironment != "" {

systemtest/approvals/TestErrorIngest.approved.json

@@ -76,7 +76,7 @@
             "logs"
         ],
         "error.grouping_key": [
-            "d6b3f958dfea98dc9ed2b57d5f0c48bb"
+            "5be7ecce1b964f32"
         ],
         "error.grouping_name": [
             "Cannot read property 'baz' of undefined"

systemtest/approvals/TestIntake/Errors.approved.json

@@ -118,7 +118,7 @@
             "ConnectionError"
         ],
         "error.grouping_key": [
-            "d72b25a26fde3f3aaad1c86950acd070"
+            "637be2ded470655b"
         ],
         "error.grouping_name": [
             "My service could not talk to the database named foobar"
@@ -439,7 +439,7 @@
             "Cannot read property 'baz' no defined"
         ],
         "error.grouping_key": [
-            "ae0232fed4cb40e7ebc62a585a421d60"
+            "89f9636ef3381842"
         ],
         "error.grouping_name": [
             "Cannot read property 'baz' no defined"
@@ -655,7 +655,7 @@
             "logs"
         ],
         "error.grouping_key": [
-            "dc8dd667f7036ec5f0bae87bf2188243"
+            "256d70df2f0019ed"
         ],
         "error.grouping_name": [
             "no user found"
@@ -880,7 +880,7 @@
             "DbError"
         ],
         "error.grouping_key": [
-            "c3868d6704b923014eaffea034e70a3d"
+            "60b29d2f9dafe754"
         ],
         "error.id": [
             "cdefab0123456780"
@@ -1096,7 +1096,7 @@
             "logs"
         ],
         "error.grouping_key": [
-            "d6b3f958dfea98dc9ed2b57d5f0c48bb"
+            "5be7ecce1b964f32"
         ],
         "error.grouping_name": [
             "Cannot read property 'baz' of undefined"

systemtest/approvals/TestIntake/ErrorsTxID.approved.json

@@ -58,7 +58,7 @@
             "ConnectionError"
         ],
         "error.grouping_key": [
-            "9a4054e958afe722b5877e8fac578ff3"
+            "676837116a6f59d2"
         ],
         "error.grouping_name": [
             "Request method 'POST' not supported"

systemtest/approvals/TestIntake/Events.approved.json

@@ -61,7 +61,7 @@
             "ConnectionError"
         ],
         "error.grouping_key": [
-            "9a4054e958afe722b5877e8fac578ff3"
+            "676837116a6f59d2"
         ],
         "error.grouping_name": [
             "Request method 'POST' not supported"

systemtest/approvals/TestIntake/MinimalEvents.approved.json

@@ -22,7 +22,7 @@
             "logs"
         ],
         "error.grouping_key": [
-            "0b9cba09845a097a271c6beb4c6207f3"
+            "e7427150b064c482"
         ],
         "error.grouping_name": [
             "error log message"
@@ -90,7 +90,7 @@
             "error exception message"
         ],
         "error.grouping_key": [
-            "3a1fb5609458fbb132b44d8fc7cde104"
+            "5914882bfc6424ff"
         ],
         "error.grouping_name": [
             "error exception message"
@@ -152,7 +152,7 @@
             "error exception type"
         ],
         "error.grouping_key": [
-            "fa405fa2bd848dab17207e7b544d9ad4"
+            "0726afd6fffc5433"
         ],
         "error.id": [
             "abcdef0123456791"

systemtest/approvals/TestOTLPGRPCTraces.approved.json

@@ -31,7 +31,7 @@
             "*errors.errorString"
         ],
         "error.grouping_key": [
-            "14f4d08792a45fce53a46c93851e36e1"
+            "7f440eedb20ba958"
         ],
         "error.grouping_name": [
             "kablamo"

systemtest/approvals/TestRUMErrorSourcemapping/absolute_bundle_filepath/standalone.approved.json

@@ -34,7 +34,7 @@
             "Error"
         ],
         "error.grouping_key": [
-            "89e23da755c2dd759d2d529e37c92b8f"
+            "9b83ced5381eaafe"
         ],
         "error.grouping_name": [
             "Uncaught Error: log timeout test error"

systemtest/approvals/TestRUMErrorSourcemapping/relative_bundle_filepath/standalone.approved.json

@@ -34,7 +34,7 @@
             "Error"
         ],
         "error.grouping_key": [
-            "89e23da755c2dd759d2d529e37c92b8f"
+            "9b83ced5381eaafe"
         ],
         "error.grouping_name": [
             "Uncaught Error: log timeout test error"