[receiver/mongodbatlasreceiver] add metrics project config (#28866)

**Description:** <Describe what has changed.>
<!--Ex. Fixing a bug - Describe the bug and how this fixes the issue.
Ex. Adding a feature - Explain what this achieves.-->
This feature adds a Project Config for the metrics to filter by Project
name and or clusters.

**Link to tracking Issue:** <Issue number if applicable>
#28865 

**Testing:** <Describe what testing was performed and which tests were
added.>
- Added test for cluster filtering
- Tested project name alone, project name with IncludeClusters and
project name with ExcludeClusters on a live environment with success.

**Documentation:** <Describe the documentation added.>
Added optional project config fields to README

---------

Co-authored-by: Daniel Jaglowski <jaglows3@gmail.com>

.chloggen/mongodbatlasreceiver-add-metrics-project-config.yaml

@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# 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. filelogreceiver)
+component: receiver/mongodbatlasreceiver
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: adds project config to mongodbatlas metrics to filter by project name and clusters.
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [28865]
+
+# (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 your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: []

receiver/mongodbatlasreceiver/README.md

@@ -42,6 +42,11 @@ MongoDB Atlas [Documentation](https://www.mongodb.com/docs/atlas/reference/api/l
 - `granularity` (default `PT1M` - See [MongoDB Atlas Documentation](https://docs.atlas.mongodb.com/reference/api/process-measurements/))
 - `collection_interval` (default `3m`) This receiver collects metrics on an interval. Valid time units are `ns`, `us` (or `µs`), `ms`, `s`, `m`, `h`.
 - `storage` (optional) The component ID of a storage extension which can be used when polling for `alerts` or `events` . The storage extension prevents duplication of data after a collector restart by remembering which data were previously collected.
+- `projects` (optional for metrics) a slice of projects this receiver collects metrics from instead of all projects in an organization
+  - `name` Name of the project to discover metrics from
+  - `include_clusters` (default empty, exclusive with `exclude_clusters`)
+  - `exclude_clusters` (default empty, exclusive with `include_clusters`)
+    - If both `include_clusters` and `exclude_clusters` are empty, then all clusters in the project will be included
 - `retry_on_failure`
   - `enabled` (default true)
   - `initial_interval` (default 5s)

receiver/mongodbatlasreceiver/config.go

@@ -28,6 +28,7 @@ type Config struct {
 	PrivateKey                              configopaque.String           `mapstructure:"private_key"`
 	Granularity                             string                        `mapstructure:"granularity"`
 	MetricsBuilderConfig                    metadata.MetricsBuilderConfig `mapstructure:",squash"`
+	Projects                                []*ProjectConfig              `mapstructure:"projects"`
 	Alerts                                  AlertConfig                   `mapstructure:"alerts"`
 	Events                                  *EventsConfig                 `mapstructure:"events"`
 	Logs                                    LogConfig                     `mapstructure:"logs"`
@@ -133,6 +134,12 @@ var (
 func (c *Config) Validate() error {
 	var errs error
 
+	for _, project := range c.Projects {
+		if len(project.ExcludeClusters) != 0 && len(project.IncludeClusters) != 0 {
+			errs = multierr.Append(errs, errClusterConfig)
+		}
+	}
+
 	errs = multierr.Append(errs, c.Alerts.validate())
 	errs = multierr.Append(errs, c.Logs.validate())
 	if c.Events != nil {

receiver/mongodbatlasreceiver/config_test.go

@@ -116,6 +116,47 @@ func TestValidate(t *testing.T) {
 			},
 			expectedErr: errNoCert.Error(),
 		},
+		{
+			name: "Valid Metrics Config",
+			input: Config{
+				Projects: []*ProjectConfig{
+					{
+						Name: "Project1",
+					},
+				},
+				ScraperControllerSettings: scraperhelper.NewDefaultScraperControllerSettings(metadata.Type),
+			},
+		},
+		{
+			name: "Valid Metrics Config with multiple projects with an inclusion or exclusion",
+			input: Config{
+				Projects: []*ProjectConfig{
+					{
+						Name:            "Project1",
+						IncludeClusters: []string{"Cluster1"},
+					},
+					{
+						Name:            "Project2",
+						ExcludeClusters: []string{"Cluster1"},
+					},
+				},
+				ScraperControllerSettings: scraperhelper.NewDefaultScraperControllerSettings(metadata.Type),
+			},
+		},
+		{
+			name: "invalid Metrics Config",
+			input: Config{
+				Projects: []*ProjectConfig{
+					{
+						Name:            "Project1",
+						IncludeClusters: []string{"Cluster1"},
+						ExcludeClusters: []string{"Cluster2"},
+					},
+				},
+				ScraperControllerSettings: scraperhelper.NewDefaultScraperControllerSettings(metadata.Type),
+			},
+			expectedErr: errClusterConfig.Error(),
+		},
 		{
 			name: "Valid Logs Config",
 			input: Config{

receiver/mongodbatlasreceiver/receiver.go

@@ -37,6 +37,10 @@ type timeconstraints struct {
 
 func newMongoDBAtlasReceiver(settings receiver.CreateSettings, cfg *Config) *mongodbatlasreceiver {
 	client := internal.NewMongoDBAtlasClient(cfg.PublicKey, string(cfg.PrivateKey), cfg.RetrySettings, settings.Logger)
+	for _, p := range cfg.Projects {
+		p.populateIncludesAndExcludes()
+	}
+
 	return &mongodbatlasreceiver{
 		log:         settings.Logger,
 		cfg:         cfg,
@@ -77,47 +81,113 @@ func (s *mongodbatlasreceiver) shutdown(context.Context) error {
 	return s.client.Shutdown()
 }
 
+// poll decides whether to poll all projects or a specific project based on the configuration.
 func (s *mongodbatlasreceiver) poll(ctx context.Context, time timeconstraints) error {
+	if len(s.cfg.Projects) == 0 {
+		return s.pollAllProjects(ctx, time)
+	}
+	return s.pollProjects(ctx, time)
+}
+
+// pollAllProjects handles polling across all projects within the organizations.
+func (s *mongodbatlasreceiver) pollAllProjects(ctx context.Context, time timeconstraints) error {
 	orgs, err := s.client.Organizations(ctx)
 	if err != nil {
 		return fmt.Errorf("error retrieving organizations: %w", err)
 	}
 	for _, org := range orgs {
-		projects, err := s.client.Projects(ctx, org.ID)
+		proj, err := s.client.Projects(ctx, org.ID)
 		if err != nil {
-			return fmt.Errorf("error retrieving projects: %w", err)
+			s.log.Error("error retrieving projects", zap.String("orgID", org.ID), zap.Error(err))
+			continue
 		}
-		for _, project := range projects {
-			nodeClusterMap, providerMap, err := s.getNodeClusterNameMap(ctx, project.ID)
-			if err != nil {
-				return fmt.Errorf("error collecting clusters from project %s: %w", project.ID, err)
+		for _, project := range proj {
+			// Since there is no specific ProjectConfig for these projects, pass nil.
+			if err := s.processProject(ctx, time, org.Name, project, nil); err != nil {
+				s.log.Error("error processing project", zap.String("projectID", project.ID), zap.Error(err))
 			}
+		}
+	}
+	return nil
+}
 
-			processes, err := s.client.Processes(ctx, project.ID)
-			if err != nil {
-				return fmt.Errorf("error retrieving MongoDB Atlas processes for project %s: %w", project.ID, err)
-			}
-			for _, process := range processes {
-				clusterName := nodeClusterMap[process.UserAlias]
-				providerValues := providerMap[clusterName]
+// pollProject handles polling for specific projects as configured.
+func (s *mongodbatlasreceiver) pollProjects(ctx context.Context, time timeconstraints) error {
+	for _, projectCfg := range s.cfg.Projects {
+		project, err := s.client.GetProject(ctx, projectCfg.Name)
+		if err != nil {
+			s.log.Error("error retrieving project", zap.String("projectName", projectCfg.Name), zap.Error(err))
+			continue
+		}
 
-				if err := s.extractProcessMetrics(ctx, time, org.Name, project, process, clusterName, providerValues); err != nil {
-					return fmt.Errorf("error when polling process metrics from MongoDB Atlas for process %s: %w", process.ID, err)
-				}
+		org, err := s.client.GetOrganization(ctx, project.OrgID)
+		if err != nil {
+			s.log.Error("error retrieving organization from project", zap.String("projectName", projectCfg.Name), zap.Error(err))
+			continue
+		}
 
-				if err := s.extractProcessDatabaseMetrics(ctx, time, org.Name, project, process, clusterName, providerValues); err != nil {
-					return fmt.Errorf("error when polling process database metrics from MongoDB Atlas for process %s: %w", process.ID, err)
-				}
+		if err := s.processProject(ctx, time, org.Name, project, projectCfg); err != nil {
+			s.log.Error("error processing project", zap.String("projectID", project.ID), zap.Error(err))
+		}
+	}
+	return nil
+}
 
-				if err := s.extractProcessDiskMetrics(ctx, time, org.Name, project, process, clusterName, providerValues); err != nil {
-					return fmt.Errorf("error when polling process disk metrics from MongoDB Atlas for process %s: %w", process.ID, err)
-				}
-			}
+func (s *mongodbatlasreceiver) processProject(ctx context.Context, time timeconstraints, orgName string, project *mongodbatlas.Project, projectCfg *ProjectConfig) error {
+	nodeClusterMap, providerMap, err := s.getNodeClusterNameMap(ctx, project.ID)
+	if err != nil {
+		return fmt.Errorf("error collecting clusters from project %s: %w", project.ID, err)
+	}
+
+	processes, err := s.client.Processes(ctx, project.ID)
+	if err != nil {
+		return fmt.Errorf("error retrieving MongoDB Atlas processes for project %s: %w", project.ID, err)
+	}
+
+	for _, process := range processes {
+		clusterName := nodeClusterMap[process.UserAlias]
+		providerValues := providerMap[clusterName]
+
+		if !shouldProcessCluster(projectCfg, clusterName) {
+			// Skip processing for this cluster
+			continue
+		}
+
+		if err := s.extractProcessMetrics(ctx, time, orgName, project, process, clusterName, providerValues); err != nil {
+			return fmt.Errorf("error when polling process metrics from MongoDB Atlas for process %s: %w", process.ID, err)
+		}
+
+		if err := s.extractProcessDatabaseMetrics(ctx, time, orgName, project, process, clusterName, providerValues); err != nil {
+			return fmt.Errorf("error when polling process database metrics from MongoDB Atlas for process %s: %w", process.ID, err)
+		}
+
+		if err := s.extractProcessDiskMetrics(ctx, time, orgName, project, process, clusterName, providerValues); err != nil {
+			return fmt.Errorf("error when polling process disk metrics from MongoDB Atlas for process %s: %w", process.ID, err)
 		}
 	}
+
 	return nil
 }
 
+// shouldProcessCluster checks whether a given cluster should be processed based on the project configuration.
+func shouldProcessCluster(projectCfg *ProjectConfig, clusterName string) bool {
+	if projectCfg == nil {
+		// If there is no project config, process all clusters.
+		return true
+	}
+
+	_, isIncluded := projectCfg.includesByClusterName[clusterName]
+	_, isExcluded := projectCfg.excludesByClusterName[clusterName]
+
+	// Return false immediately if the cluster is excluded.
+	if isExcluded {
+		return false
+	}
+
+	// If IncludeClusters is empty, or the cluster is explicitly included, return true.
+	return len(projectCfg.IncludeClusters) == 0 || isIncluded
+}
+
 type providerValues struct {
 	RegionName   string
 	ProviderName string

receiver/mongodbatlasreceiver/receiver_test.go

@@ -71,3 +71,69 @@ func TestTimeConstraints(t *testing.T) {
 		t.Run(testCase.name, testCase.run)
 	}
 }
+
+func TestShouldProcessCluster(t *testing.T) {
+	tests := []struct {
+		name        string
+		projectCfg  *ProjectConfig
+		clusterName string
+		want        bool
+	}{
+		{
+			name: "included cluster should be processed",
+			projectCfg: &ProjectConfig{
+				IncludeClusters: []string{"Cluster1"},
+			},
+			clusterName: "Cluster1",
+			want:        true,
+		},
+		{
+			name: "cluster not included should not be processed",
+			projectCfg: &ProjectConfig{
+				IncludeClusters: []string{"Cluster1"},
+			},
+			clusterName: "Cluster2",
+			want:        false,
+		},
+		{
+			name: "excluded cluster should not be processed",
+			projectCfg: &ProjectConfig{
+				ExcludeClusters: []string{"Cluster2"},
+			},
+			clusterName: "Cluster2",
+			want:        false,
+		},
+		{
+			name: "cluster not excluded should processed assuming it exists in the project",
+			projectCfg: &ProjectConfig{
+				ExcludeClusters: []string{"Cluster1"},
+			},
+			clusterName: "Cluster2",
+			want:        true,
+		},
+		{
+			name:        "cluster should be processed when no includes or excludes are set",
+			projectCfg:  &ProjectConfig{},
+			clusterName: "Cluster1",
+			want:        true,
+		},
+		{
+			name:        "cluster should be processed when no includes or excludes are set and cluster name is empty",
+			projectCfg:  nil,
+			clusterName: "Cluster1",
+			want:        true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.projectCfg != nil {
+				tt.projectCfg.populateIncludesAndExcludes()
+			}
+
+			if got := shouldProcessCluster(tt.projectCfg, tt.clusterName); got != tt.want {
+				t.Errorf("shouldProcessCluster() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}