feat(database_observability): update default excluded schemas and users

Exclude by default well known databases/schemas and users from cloud
providers.

Author: cristiangreco

docs/sources/reference/components/database_observability/database_observability.mysql.md

@@ -34,7 +34,7 @@ You can use the following arguments with `database_observability.mysql`:
 | `targets`                                  | `list(map(string))`  | List of external targets to scrape.                                         |         | no       |
 | `disable_collectors`                       | `list(string)`       | A list of collectors to disable from the default set.                       |         | no       |
 | `enable_collectors`                        | `list(string)`       | A list of collectors to enable on top of the default set.                   |         | no       |
-| `exclude_schemas`                          | `list(string)`       | A list of schemas to exclude from monitoring.                               |         | no       |
+| `exclude_schemas`                          | `list(string)`       | A list of schemas to exclude from monitoring.                               | `["alloydbadmin", "alloydbmetadata", "azure_maintenance", "azure_sys", "cloudsqladmin", "rdsadmin"]` | no       |
 | `allow_update_performance_schema_settings` | `boolean`            | Whether to allow updates to `performance_schema` settings in any collector. Enable this in conjunction with other collector-specific settings where required. | `false` | no       |
 
 The following collectors are configurable:

docs/sources/reference/components/database_observability/database_observability.postgres.md

@@ -34,8 +34,8 @@ You can use the following arguments with `database_observability.postgres`:
 | `targets`            | `list(map(string))`  | List of external targets to scrape for Prometheus metrics.  |         | no       |
 | `disable_collectors` | `list(string)`       | A list of collectors to disable from the default set.       |         | no       |
 | `enable_collectors`  | `list(string)`       | A list of collectors to enable on top of the default set.   |         | no       |
-| `exclude_databases`  | `list(string)`       | A list of databases to exclude from monitoring.             |         | no       |
-| `exclude_users`      | `list(string)`       | A list of users to exclude from monitoring.                 |         | no       |
+| `exclude_databases`  | `list(string)`       | A list of databases to exclude from monitoring.             | `["alloydbadmin", "alloydbmetadata", "azure_maintenance", "azure_sys", "cloudsqladmin", "rdsadmin"]` | no       |
+| `exclude_users`      | `list(string)`       | A list of users to exclude from monitoring.                 | `["azuresu", "cloudsqladmin", "db-o11y", "rdsadmin"]` | no       |
 
 [Data Source Name]: https://pkg.go.dev/github.com/lib/pq#hdr-URL_connection_strings-NewConfig
 

internal/component/database_observability/mysql/component.go

@@ -163,7 +163,7 @@ func (a *PrometheusExporterArguments) Validate() error {
 }
 
 var DefaultArguments = Arguments{
-	ExcludeSchemas:                []string{},
+	ExcludeSchemas:                database_observability.DefaultExcludedSchemas(),
 	AllowUpdatePerfSchemaSettings: false,
 
 	QueryDetailsArguments: QueryDetailsArguments{

internal/component/database_observability/mysql/component_test.go

@@ -28,6 +28,27 @@ import (
 	"github.com/grafana/loki/pkg/push"
 )
 
+func Test_defaultExclusions(t *testing.T) {
+	exampleDBO11yAlloyConfig := `
+		data_source_name = ""
+		forward_to = []
+		targets = []
+	`
+
+	var args Arguments
+	err := syntax.Unmarshal([]byte(exampleDBO11yAlloyConfig), &args)
+	require.NoError(t, err)
+
+	assert.Equal(t, []string{
+		"rdsadmin",
+		"cloudsqladmin",
+		"azure_sys",
+		"azure_maintenance",
+		"alloydbadmin",
+		"alloydbmetadata",
+	}, args.ExcludeSchemas)
+}
+
 func Test_disableQueryRedaction(t *testing.T) {
 	t.Run("enable sql text when provided", func(t *testing.T) {
 		exampleDBO11yAlloyConfig := `

internal/component/database_observability/postgres/component.go

@@ -121,8 +121,8 @@ type SchemaDetailsArguments struct {
 }
 
 var DefaultArguments = Arguments{
-	ExcludeDatabases: []string{},
-	ExcludeUsers:     []string{},
+	ExcludeDatabases: database_observability.DefaultExcludedDatabases(),
+	ExcludeUsers:     database_observability.DefaultExcludedUsers(),
 	QuerySampleArguments: QuerySampleArguments{
 		CollectInterval:       15 * time.Second,
 		DisableQueryRedaction: false,

internal/component/database_observability/postgres/component_test.go

@@ -63,6 +63,34 @@ func newTestComponent(t *testing.T, openSQL func(string, string) (*sql.DB, error
 	return c
 }
 
+func Test_defaultExclusions(t *testing.T) {
+	exampleDBO11yAlloyConfig := `
+		data_source_name = "postgres://db"
+		forward_to = []
+		targets = []
+	`
+
+	var args Arguments
+	err := syntax.Unmarshal([]byte(exampleDBO11yAlloyConfig), &args)
+	require.NoError(t, err)
+
+	assert.Equal(t, []string{
+		"rdsadmin",
+		"cloudsqladmin",
+		"azure_sys",
+		"azure_maintenance",
+		"alloydbadmin",
+		"alloydbmetadata",
+	}, args.ExcludeDatabases)
+
+	assert.Equal(t, []string{
+		"db-o11y",
+		"rdsadmin",
+		"cloudsqladmin",
+		"azuresu",
+	}, args.ExcludeUsers)
+}
+
 func Test_enableOrDisableCollectors(t *testing.T) {
 	t.Run("nothing specified (default behavior)", func(t *testing.T) {
 		exampleDBO11yAlloyConfig := `

internal/component/database_observability/sql_exclusion.go

@@ -1,6 +1,37 @@
 package database_observability
 
-import "strings"
+import (
+	"slices"
+	"strings"
+)
+
+var defaultExcludedSchemas = []string{
+	"alloydbadmin",
+	"alloydbmetadata",
+	"azure_maintenance",
+	"azure_sys",
+	"cloudsqladmin",
+	"rdsadmin",
+}
+
+var defaultExcludedUsers = []string{
+	"azuresu",
+	"cloudsqladmin",
+	"db-o11y", // default recommended user
+	"rdsadmin",
+}
+
+func DefaultExcludedDatabases() []string {
+	return slices.Clone(defaultExcludedSchemas)
+}
+
+func DefaultExcludedSchemas() []string {
+	return slices.Clone(defaultExcludedSchemas)
+}
+
+func DefaultExcludedUsers() []string {
+	return slices.Clone(defaultExcludedUsers)
+}
 
 // BuildExclusionClause builds a SQL IN clause from a list of items.
 func BuildExclusionClause(items []string) string {