Support excluding specific postgresql databases from stats collection (open-telemetry#29605)

**Description:**
There are cases where all except a few databases should be collected,
for example the `rdsadmin` database in Amazon RDS is not accessible to
regular users. This PR adds an `exclude_databases` config setting to the
psql collector where it's possible to specify a list of databases that
should be excluded.

**Testing:**

Unit tests added

**Documentation:** 

Readme updated with new config setting

---------

Co-authored-by: Daniel Jaglowski <[email protected]>

Author: 2 people

.chloggen/postgresql-exclude.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: postgresqlreceiver
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Add config property for excluding specific databases from scraping
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [29605]
+
+# (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/postgresqlreceiver/README.md

@@ -39,6 +39,8 @@ The following settings are optional:
 
 - `databases` (default = `[]`): The list of databases for which the receiver will attempt to collect statistics. If an empty list is provided, the receiver will attempt to collect statistics for all non-template databases.
 
+- `exclude_databases` (default = `[]`): List of databases which will be excluded when collecting statistics.
+
 The following settings are also optional and nested under `tls` to help configure client transport security
 
 - `insecure` (default = `false`): Whether to enable client transport security for the postgresql connection.
@@ -70,7 +72,7 @@ receivers:
       key_file: /home/otel/mypostgreskey.key
 ```
 
-The full list of settings exposed for this receiver are documented [here](./config.go) with detailed sample configurations [here](./testdata/config.yaml). TLS config is documented further under the [opentelemetry collector's configtls package](https://github.com/open-telemetry/opentelemetry-collector/blob/main/config/configtls/README.md). 
+The full list of settings exposed for this receiver are documented [here](./config.go) with detailed sample configurations [here](./testdata/config.yaml). TLS config is documented further under the [opentelemetry collector's configtls package](https://github.com/open-telemetry/opentelemetry-collector/blob/main/config/configtls/README.md).
 
 ## Metrics
 

receiver/postgresqlreceiver/config.go

@@ -31,6 +31,7 @@ type Config struct {
 	Username                                string                         `mapstructure:"username"`
 	Password                                configopaque.String            `mapstructure:"password"`
 	Databases                               []string                       `mapstructure:"databases"`
+	ExcludeDatabases                        []string                       `mapstructure:"exclude_databases"`
 	confignet.NetAddr                       `mapstructure:",squash"`       // provides Endpoint and Transport
 	configtls.TLSClientSetting              `mapstructure:"tls,omitempty"` // provides SSL details
 	metadata.MetricsBuilderConfig           `mapstructure:",squash"`

receiver/postgresqlreceiver/config_test.go

@@ -139,6 +139,7 @@ func TestLoadConfig(t *testing.T) {
 		expected.Username = "otel"
 		expected.Password = "${env:POSTGRESQL_PASSWORD}"
 		expected.Databases = []string{"otel"}
+		expected.ExcludeDatabases = []string{"template0"}
 		expected.CollectionInterval = 10 * time.Second
 		expected.TLSClientSetting = configtls.TLSClientSetting{
 			Insecure:           false,

receiver/postgresqlreceiver/scraper.go

@@ -24,6 +24,7 @@ type postgreSQLScraper struct {
 	config        *Config
 	clientFactory postgreSQLClientFactory
 	mb            *metadata.MetricsBuilder
+	excludes      map[string]struct{}
 }
 type errsMux struct {
 	sync.RWMutex
@@ -69,11 +70,16 @@ func newPostgreSQLScraper(
 	config *Config,
 	clientFactory postgreSQLClientFactory,
 ) *postgreSQLScraper {
+	excludes := make(map[string]struct{})
+	for _, db := range config.ExcludeDatabases {
+		excludes[db] = struct{}{}
+	}
 	return &postgreSQLScraper{
 		logger:        settings.Logger,
 		config:        config,
 		clientFactory: clientFactory,
 		mb:            metadata.NewMetricsBuilder(config.MetricsBuilderConfig, settings),
+		excludes:      excludes,
 	}
 }
 
@@ -102,6 +108,13 @@ func (p *postgreSQLScraper) scrape(ctx context.Context) (pmetric.Metrics, error)
 		}
 		databases = dbList
 	}
+	var filteredDatabases []string
+	for _, db := range databases {
+		if _, ok := p.excludes[db]; !ok {
+			filteredDatabases = append(filteredDatabases, db)
+		}
+	}
+	databases = filteredDatabases
 
 	now := pcommon.NewTimestampFromTime(time.Now())
 

receiver/postgresqlreceiver/scraper_test.go

@@ -207,6 +207,27 @@ func TestScraperWithResourceAttributeFeatureGateSingle(t *testing.T) {
 		pmetrictest.IgnoreMetricDataPointsOrder(), pmetrictest.IgnoreStartTimestamp(), pmetrictest.IgnoreTimestamp()))
 }
 
+func TestScraperExcludeDatabase(t *testing.T) {
+	factory := mockClientFactory{}
+	factory.initMocks([]string{"otel", "telemetry"})
+
+	cfg := createDefaultConfig().(*Config)
+	cfg.ExcludeDatabases = []string{"open"}
+
+	scraper := newPostgreSQLScraper(receivertest.NewNopCreateSettings(), cfg, &factory)
+
+	actualMetrics, err := scraper.scrape(context.Background())
+	require.NoError(t, err)
+
+	expectedFile := filepath.Join("testdata", "scraper", "multiple", "exclude.yaml")
+
+	expectedMetrics, err := golden.ReadMetrics(expectedFile)
+	require.NoError(t, err)
+
+	require.NoError(t, pmetrictest.CompareMetrics(expectedMetrics, actualMetrics, pmetrictest.IgnoreResourceMetricsOrder(),
+		pmetrictest.IgnoreMetricDataPointsOrder(), pmetrictest.IgnoreStartTimestamp(), pmetrictest.IgnoreTimestamp()))
+}
+
 type mockClientFactory struct{ mock.Mock }
 type mockClient struct{ mock.Mock }
 

receiver/postgresqlreceiver/testdata/config.yaml

@@ -9,6 +9,8 @@ postgresql/all:
   password: ${env:POSTGRESQL_PASSWORD}
   databases:
     - otel
+  exclude_databases:
+    - template0
   collection_interval: 10s
   tls:
     insecure: false