Implements file reading for peer tags to synchronize cross repo usage

comp/otelcol/otlp/components/statsprocessor/go.mod

@@ -101,6 +101,7 @@ require (
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20240401170217-c3f982113cda // indirect
 	google.golang.org/grpc v1.63.2 // indirect
 	google.golang.org/protobuf v1.34.1 // indirect
+	gopkg.in/ini.v1 v1.67.0 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

pkg/trace/go.mod

@@ -45,6 +45,7 @@ require (
 	golang.org/x/time v0.5.0
 	google.golang.org/grpc v1.63.2
 	google.golang.org/protobuf v1.34.0
+	gopkg.in/ini.v1 v1.67.0
 	k8s.io/apimachinery v0.25.5
 )
 

pkg/trace/stats/concentrator.go

@@ -6,11 +6,14 @@
 package stats
 
 import (
+	_ "embed"
 	"sort"
 	"strings"
 	"sync"
 	"time"
 
+	"gopkg.in/ini.v1"
+
 	pb "github.com/DataDog/datadog-agent/pkg/proto/pbgo/trace"
 	"github.com/DataDog/datadog-agent/pkg/trace/config"
 	"github.com/DataDog/datadog-agent/pkg/trace/log"
@@ -55,37 +58,28 @@ type Concentrator struct {
 	statsd                 statsd.ClientInterface
 }
 
-var defaultPeerTags = []string{
-	"_dd.base_service",
-	"amqp.destination",
-	"amqp.exchange",
-	"amqp.queue",
-	"aws.queue.name",
-	"bucketname",
-	"cassandra.cluster",
-	"db.cassandra.contact.points",
-	"db.couchbase.seed.nodes",
-	"db.hostname",
-	"db.instance",
-	"db.name",
-	"db.system",
-	"hazelcast.instance",
-	"messaging.kafka.bootstrap.servers",
-	"mongodb.db",
-	"msmq.queue.path",
-	"net.peer.name",
-	"network.destination.name",
-	"peer.hostname",
-	"peer.service",
-	"queuename",
-	"rpc.service",
-	"rulename",
-	"server.address",
-	"statemachinename",
-	"streamname",
-	"tablename",
-	"topicname",
-}
+//go:embed peer_tags.ini
+var peerTagFile []byte
+
+var defaultPeerTags = func() []string {
+	var tags []string = []string{"_dd.base_service"}
+
+	cfg, err := ini.Load(peerTagFile)
+	if err != nil {
+		log.Error("Error loading file for peer tags: ", err)
+		return tags
+	}
+	keys := cfg.Section("dd.apm.peer.tags").Keys()
+
+	for _, key := range keys {
+		value := strings.Split(key.Value(), ",")
+		tags = append(tags, value...)
+	}
+
+	sort.Strings(tags)
+
+	return tags
+}()
 
 func preparePeerTags(tags ...string) []string {
 	if len(tags) == 0 {

pkg/trace/stats/concentrator_test.go

@@ -1062,3 +1062,52 @@ func TestPreparePeerTags(t *testing.T) {
 		assert.Equal(t, tc.output, preparePeerTags(tc.input...))
 	}
 }
+
+func TestDefaultPeerTags(t *testing.T) {
+	expectedListOfPeerTags := []string{
+		"_dd.base_service",
+		"amqp.destination",
+		"amqp.exchange",
+		"amqp.queue",
+		"aws.queue.name",
+		"aws.s3.bucket",
+		"bucketname",
+		"cassandra.keyspace",
+		"db.cassandra.contact.points",
+		"db.couchbase.seed.nodes",
+		"db.hostname",
+		"db.instance",
+		"db.name",
+		"db.namespace",
+		"db.system",
+		"grpc.host",
+		"hostname",
+		"http.host",
+		"http.server_name",
+		"messaging.destination",
+		"messaging.destination.name",
+		"messaging.kafka.bootstrap.servers",
+		"messaging.rabbitmq.exchange",
+		"messaging.system",
+		"mongodb.db",
+		"msmq.queue.path",
+		"net.peer.name",
+		"network.destination.name",
+		"peer.hostname",
+		"peer.service",
+		"queuename",
+		"rpc.service",
+		"rpc.system",
+		"server.address",
+		"streamname",
+		"tablename",
+		"topicname",
+	}
+	actualListOfPeerTags := defaultPeerTags
+
+	// Sort both arrays for comparison
+	sort.Strings(actualListOfPeerTags)
+	sort.Strings(expectedListOfPeerTags)
+
+	assert.Equal(t, expectedListOfPeerTags, actualListOfPeerTags)
+}

pkg/trace/stats/peer_tags.ini

@@ -0,0 +1,21 @@
+# if a peer entity tag is expected to be set at the tracer, and we want to keep it, then it must be included
+# in the list. I.e., since we have at least one tracer which actually sets `peer.hostname` directly, we need
+# to set `peer.hostname = "peer.hostname" else it will get stripped out
+# the order of the precursors matters, as it is "first one wins". so if we expect some spans to have more than one
+# precursor, and the precursors may not always have the exact same meaning, then put the higher priority one at the front
+[dd.apm.peer.tags]
+peer.aws.dynamodb.table = "tablename"
+peer.aws.kinesis.stream = "streamname"
+peer.aws.s3.bucket = "bucketname,aws.s3.bucket"
+peer.aws.sqs.queue = "queuename"
+peer.cassandra.contact.points = "db.cassandra.contact.points"
+peer.couchbase.seed.nodes = "db.couchbase.seed.nodes"
+peer.db.name = "db.name,mongodb.db,db.instance,cassandra.keyspace,db.namespace"
+peer.db.system = "db.system"
+peer.hostname = "peer.hostname,hostname,net.peer.name,db.hostname,network.destination.name,grpc.host,http.host,server.address,http.server_name"
+peer.kafka.bootstrap.servers = "messaging.kafka.bootstrap.servers"
+peer.messaging.destination = "topicname,messaging.destination,messaging.destination.name,messaging.rabbitmq.exchange,amqp.destination,amqp.queue,amqp.exchange,msmq.queue.path,aws.queue.name"
+peer.messaging.system = "messaging.system"
+peer.rpc.service = "rpc.service"
+peer.rpc.system = "rpc.system"
+peer.service = "peer.service"