Merge branch 'main' into scrape_config_probe_selector

Author: dominicqi

.chloggen/3427.yaml

@@ -0,0 +1,16 @@
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. collector, target allocator, auto-instrumentation, opamp, github action)
+component: collector
+
+# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Create RBAC rules for the k8s_cluster receiver automatically.
+
+# One or more tracking issues related to the change
+issues: [3427]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:

.chloggen/3432.yaml

@@ -0,0 +1,16 @@
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. collector, target allocator, auto-instrumentation, opamp, github action)
+component: collector
+
+# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Add a warning message when one created collector needs extra RBAC permissions and the service account doesn't have them.
+
+# One or more tracking issues related to the change
+issues: [3432]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:

.chloggen/add_fallback_strategy_for_per_node_strategy.yaml

@@ -0,0 +1,21 @@
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: 'enhancement'
+
+# The name of the component, or a single word describing the area of concern, (e.g. collector, target allocator, auto-instrumentation, opamp, github action)
+component: target allocator
+
+# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Added allocation_fallback_strategy option as fallback strategy for per-node allocation strategy, can be enabled with feature flag operator.targetallocator.fallbackstrategy
+
+# One or more tracking issues related to the change
+issues: [3477]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext: |
+  If using per-node allocation strategy, targets that are not attached to a node will not
+  be allocated. As the per-node strategy is required when running as a daemonset, it is 
+  not possible to assign some targets under a daemonset deployment.
+  Feature flag operator.targetallocator.fallbackstrategy has been added and results in consistent-hashing
+  being used as the fallback allocation strategy for "per-node" only at this time.

.chloggen/bump-base-instrumentation-mem-limit.yaml

@@ -0,0 +1,16 @@
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: bug_fix
+
+# The name of the component, or a single word describing the area of concern, (e.g. collector, target allocator, auto-instrumentation, opamp, github action)
+component: auto-instrumentation
+
+# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Bump base memory requirements for python and go
+
+# One or more tracking issues related to the change
+issues: [3479]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:

.chloggen/chore_change-kube-rbac-proxy-image-registry.yaml

@@ -0,0 +1,16 @@
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. collector, target allocator, auto-instrumentation, opamp, github action)
+component: operator
+
+# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Replace references to gcr.io/kubebuilder/kube-rbac-proxy with quay.io/brancz/kube-rbac-proxy
+
+# One or more tracking issues related to the change
+issues: [3485]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:

.github/workflows/publish-autoinstrumentation-nodejs.yaml

@@ -26,7 +26,7 @@ jobs:
       - uses: actions/checkout@v4
 
       - name: Read version
-        run: echo VERSION=$(cat autoinstrumentation/nodejs/package.json | jq -r '.dependencies."@opentelemetry/sdk-node"') >> $GITHUB_ENV
+        run: echo VERSION=$(cat autoinstrumentation/nodejs/package.json | jq -r '.dependencies."@opentelemetry/auto-instrumentations-node"') >> $GITHUB_ENV
 
       - name: Docker meta
         id: meta

Makefile

@@ -206,6 +206,7 @@ add-rbac-permissions-to-operator: manifests kustomize
 	# This folder is ignored by .gitignore
 	mkdir -p config/rbac/extra-permissions-operator
 	cp -r tests/e2e-automatic-rbac/extra-permissions-operator/* config/rbac/extra-permissions-operator
+	cd config/rbac && $(KUSTOMIZE) edit add patch --kind ClusterRole --name manager-role --path extra-permissions-operator/clusterresourcequotas.yaml
 	cd config/rbac && $(KUSTOMIZE) edit add patch --kind ClusterRole --name manager-role --path extra-permissions-operator/cronjobs.yaml
 	cd config/rbac && $(KUSTOMIZE) edit add patch --kind ClusterRole --name manager-role --path extra-permissions-operator/daemonsets.yaml
 	cd config/rbac && $(KUSTOMIZE) edit add patch --kind ClusterRole --name manager-role --path extra-permissions-operator/events.yaml

apis/v1alpha1/instrumentation_webhook.go

@@ -128,13 +128,13 @@ func (w InstrumentationWebhook) defaulter(r *Instrumentation) error {
 	if r.Spec.Python.Resources.Limits == nil {
 		r.Spec.Python.Resources.Limits = corev1.ResourceList{
 			corev1.ResourceCPU:    resource.MustParse("500m"),
-			corev1.ResourceMemory: resource.MustParse("32Mi"),
+			corev1.ResourceMemory: resource.MustParse("64Mi"),
 		}
 	}
 	if r.Spec.Python.Resources.Requests == nil {
 		r.Spec.Python.Resources.Requests = corev1.ResourceList{
 			corev1.ResourceCPU:    resource.MustParse("50m"),
-			corev1.ResourceMemory: resource.MustParse("32Mi"),
+			corev1.ResourceMemory: resource.MustParse("64Mi"),
 		}
 	}
 	if r.Spec.DotNet.Image == "" {
@@ -158,13 +158,13 @@ func (w InstrumentationWebhook) defaulter(r *Instrumentation) error {
 	if r.Spec.Go.Resources.Limits == nil {
 		r.Spec.Go.Resources.Limits = corev1.ResourceList{
 			corev1.ResourceCPU:    resource.MustParse("500m"),
-			corev1.ResourceMemory: resource.MustParse("32Mi"),
+			corev1.ResourceMemory: resource.MustParse("64Mi"),
 		}
 	}
 	if r.Spec.Go.Resources.Requests == nil {
 		r.Spec.Go.Resources.Requests = corev1.ResourceList{
 			corev1.ResourceCPU:    resource.MustParse("50m"),
-			corev1.ResourceMemory: resource.MustParse("32Mi"),
+			corev1.ResourceMemory: resource.MustParse("64Mi"),
 		}
 	}
 	if r.Spec.ApacheHttpd.Image == "" {

autoinstrumentation/nodejs/package.json

@@ -14,17 +14,8 @@
         "typescript": "^5.6.3"
     },
     "dependencies": {
-        "@opentelemetry/api": "1.9.0",
-        "@opentelemetry/auto-instrumentations-node": "0.52.0",
+        "@opentelemetry/auto-instrumentations-node": "0.52.1",
         "@opentelemetry/exporter-metrics-otlp-grpc": "0.54.0",
-        "@opentelemetry/exporter-prometheus": "0.54.0",
-        "@opentelemetry/exporter-trace-otlp-grpc": "0.54.0",
-        "@opentelemetry/resource-detector-alibaba-cloud": "0.29.4",
-        "@opentelemetry/resource-detector-aws": "1.7.0",
-        "@opentelemetry/resource-detector-container": "0.5.0",
-        "@opentelemetry/resource-detector-gcp": "0.29.13",
-        "@opentelemetry/resources": "1.27.0",
-        "@opentelemetry/sdk-metrics": "1.27.0",
-        "@opentelemetry/sdk-node": "0.54.0"
+        "@opentelemetry/exporter-prometheus": "0.54.0"
     }
 }

bundle/community/manifests/opentelemetry-operator.clusterserviceversion.yaml

@@ -514,7 +514,7 @@ spec:
                 - --upstream=http://127.0.0.1:8080/
                 - --logtostderr=true
                 - --v=0
-                image: gcr.io/kubebuilder/kube-rbac-proxy:v0.13.1
+                image: quay.io/brancz/kube-rbac-proxy:v0.13.1
                 name: kube-rbac-proxy
                 ports:
                 - containerPort: 8443

bundle/openshift/manifests/opentelemetry-operator.clusterserviceversion.yaml

@@ -522,7 +522,7 @@ spec:
                 - --tls-private-key-file=/var/run/tls/server/tls.key
                 - --tls-cipher-suites=TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305_SHA256,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256,TLS_RSA_WITH_AES_128_GCM_SHA256,TLS_RSA_WITH_AES_256_GCM_SHA384,TLS_RSA_WITH_AES_128_CBC_SHA256
                 - --tls-min-version=VersionTLS12
-                image: gcr.io/kubebuilder/kube-rbac-proxy:v0.13.1
+                image: quay.io/brancz/kube-rbac-proxy:v0.13.1
                 name: kube-rbac-proxy
                 ports:
                 - containerPort: 8443

cmd/otel-allocator/allocation/allocator.go

@@ -76,6 +76,11 @@ func (a *allocator) SetFilter(filter Filter) {
 	a.filter = filter
 }
 
+// SetFallbackStrategy sets the fallback strategy to use.
+func (a *allocator) SetFallbackStrategy(strategy Strategy) {
+	a.strategy.SetFallbackStrategy(strategy)
+}
+
 // SetTargets accepts a list of targets that will be used to make
 // load balancing decisions. This method should be called when there are
 // new targets discovered or existing targets are shutdown.

cmd/otel-allocator/allocation/consistent_hashing.go

@@ -83,3 +83,5 @@ func (s *consistentHashingStrategy) SetCollectors(collectors map[string]*Collect
 	s.consistentHasher = consistent.New(members, s.config)
 
 }
+
+func (s *consistentHashingStrategy) SetFallbackStrategy(fallbackStrategy Strategy) {}

cmd/otel-allocator/allocation/least_weighted.go

@@ -54,3 +54,5 @@ func (s *leastWeightedStrategy) GetCollectorForTarget(collectors map[string]*Col
 }
 
 func (s *leastWeightedStrategy) SetCollectors(_ map[string]*Collector) {}
+
+func (s *leastWeightedStrategy) SetFallbackStrategy(fallbackStrategy Strategy) {}

cmd/otel-allocator/allocation/per_node.go

@@ -25,21 +25,31 @@ const perNodeStrategyName = "per-node"
 var _ Strategy = &perNodeStrategy{}
 
 type perNodeStrategy struct {
-	collectorByNode map[string]*Collector
+	collectorByNode  map[string]*Collector
+	fallbackStrategy Strategy
 }
 
 func newPerNodeStrategy() Strategy {
 	return &perNodeStrategy{
-		collectorByNode: make(map[string]*Collector),
+		collectorByNode:  make(map[string]*Collector),
+		fallbackStrategy: nil,
 	}
 }
 
+func (s *perNodeStrategy) SetFallbackStrategy(fallbackStrategy Strategy) {
+	s.fallbackStrategy = fallbackStrategy
+}
+
 func (s *perNodeStrategy) GetName() string {
 	return perNodeStrategyName
 }
 
 func (s *perNodeStrategy) GetCollectorForTarget(collectors map[string]*Collector, item *target.Item) (*Collector, error) {
 	targetNodeName := item.GetNodeName()
+	if targetNodeName == "" && s.fallbackStrategy != nil {
+		return s.fallbackStrategy.GetCollectorForTarget(collectors, item)
+	}
+
 	collector, ok := s.collectorByNode[targetNodeName]
 	if !ok {
 		return nil, fmt.Errorf("could not find collector for node %s", targetNodeName)
@@ -54,4 +64,8 @@ func (s *perNodeStrategy) SetCollectors(collectors map[string]*Collector) {
 			s.collectorByNode[collector.NodeName] = collector
 		}
 	}
+
+	if s.fallbackStrategy != nil {
+		s.fallbackStrategy.SetCollectors(collectors)
+	}
 }

cmd/otel-allocator/allocation/per_node_test.go

@@ -26,7 +26,17 @@ import (
 
 var loggerPerNode = logf.Log.WithName("unit-tests")
 
-// Tests that two targets with the same target url and job name but different label set are both added.
+func GetTargetsWithNodeName(targets []*target.Item) (targetsWithNodeName []*target.Item) {
+	for _, item := range targets {
+		if item.GetNodeName() != "" {
+			targetsWithNodeName = append(targetsWithNodeName, item)
+		}
+	}
+	return targetsWithNodeName
+}
+
+// Tests that four targets, with one of them lacking node labels, are assigned except for the
+// target that lacks node labels.
 func TestAllocationPerNode(t *testing.T) {
 	// prepare allocator with initial targets and collectors
 	s, _ := New("per-node", loggerPerNode)
@@ -93,6 +103,77 @@ func TestAllocationPerNode(t *testing.T) {
 	}
 }
 
+// Tests that four targets, with one of them missing node labels, are all assigned.
+func TestAllocationPerNodeUsingFallback(t *testing.T) {
+	// prepare allocator with initial targets and collectors
+	s, _ := New("per-node", loggerPerNode, WithFallbackStrategy(consistentHashingStrategyName))
+
+	cols := MakeNCollectors(4, 0)
+	s.SetCollectors(cols)
+	firstLabels := labels.Labels{
+		{Name: "test", Value: "test1"},
+		{Name: "__meta_kubernetes_pod_node_name", Value: "node-0"},
+	}
+	secondLabels := labels.Labels{
+		{Name: "test", Value: "test2"},
+		{Name: "__meta_kubernetes_node_name", Value: "node-1"},
+	}
+	// no label, should be allocated by the fallback strategy
+	thirdLabels := labels.Labels{
+		{Name: "test", Value: "test3"},
+	}
+	// endpointslice target kind and name
+	fourthLabels := labels.Labels{
+		{Name: "test", Value: "test4"},
+		{Name: "__meta_kubernetes_endpointslice_address_target_kind", Value: "Node"},
+		{Name: "__meta_kubernetes_endpointslice_address_target_name", Value: "node-3"},
+	}
+
+	firstTarget := target.NewItem("sample-name", "0.0.0.0:8000", firstLabels, "")
+	secondTarget := target.NewItem("sample-name", "0.0.0.0:8000", secondLabels, "")
+	thirdTarget := target.NewItem("sample-name", "0.0.0.0:8000", thirdLabels, "")
+	fourthTarget := target.NewItem("sample-name", "0.0.0.0:8000", fourthLabels, "")
+
+	targetList := map[string]*target.Item{
+		firstTarget.Hash():  firstTarget,
+		secondTarget.Hash(): secondTarget,
+		thirdTarget.Hash():  thirdTarget,
+		fourthTarget.Hash(): fourthTarget,
+	}
+
+	// test that targets and collectors are added properly
+	s.SetTargets(targetList)
+
+	// verify length
+	actualItems := s.TargetItems()
+
+	// all targets should be allocated
+	expectedTargetLen := len(targetList)
+	assert.Len(t, actualItems, expectedTargetLen)
+
+	// verify allocation to nodes
+	for targetHash, item := range targetList {
+		actualItem, found := actualItems[targetHash]
+
+		assert.True(t, found, "target with hash %s not found", item.Hash())
+
+		itemsForCollector := s.GetTargetsForCollectorAndJob(actualItem.CollectorName, actualItem.JobName)
+
+		// first two should be assigned one to each collector; if third target, it should be assigned
+		// according to the fallback strategy which may assign it to the otherwise empty collector or
+		// one of the others, depending on the strategy and collector loop order
+		if targetHash == thirdTarget.Hash() {
+			assert.Empty(t, item.GetNodeName())
+			assert.NotZero(t, len(itemsForCollector))
+			continue
+		}
+
+		// Only check targets that have been assigned using the per-node (not fallback) strategy here
+		assert.Len(t, GetTargetsWithNodeName(itemsForCollector), 1)
+		assert.Equal(t, actualItem, GetTargetsWithNodeName(itemsForCollector)[0])
+	}
+}
+
 func TestTargetsWithNoCollectorsPerNode(t *testing.T) {
 	// prepare allocator with initial targets and collectors
 	c, _ := New("per-node", loggerPerNode)