feat: add configurable name validation scheme (legacy or utf8

Signed-off-by: 7h3-3mp7y-m4n <[email protected]>

Author: 7h3-3mp7y-m4n

CHANGELOG.md

@@ -12,6 +12,7 @@
 * [FEATURE] Ruler: Add support for percentage based sharding for rulers. #6680
 * [FEATURE] Ruler: Add support for group labels. #6665
 * [FEATURE] Query federation: Introduce a regex tenant resolver to allow regex in `X-Scope-OrgID` value. #6713
+[FEATURE] Config: Name validation scheme for metric and label names can be set using the config file (`name_validation_scheme`) as well as a CLI flag (`-name.validation_scheme`)
 - Add an experimental `tenant-federation.regex-matcher-enabled` flag. If it enabled, user can input regex to `X-Scope-OrgId`, the matched tenantIDs are automatically involved. The user discovery is based on scanning block storage, so new users can get queries after uploading a block (generally 2h).
 - Add an experimental `tenant-federation.user-sync-interval` flag, it specifies how frequently to scan users. The scanned users are used to calculate matched tenantIDs.
 * [FEATURE] Experimental Support Parquet format: Implement parquet converter service to convert a TSDB block into Parquet and Parquet Queryable. #6716 #6743

docs/configuration/config-file-reference.md

@@ -68,6 +68,12 @@ Where default_value is the value to use if the environment variable is undefined
 # CLI flag: -http.prefix
 [http_prefix: <string> | default = "/api/prom"]
 
+# Validation scheme for metric and label names.
+# Set to "utf8" to allow UTF-8 characters in metric and label names.
+# Set to "legacy" to enforce strict legacy-compatible name rules.
+# CLI flag: -name.validation_scheme
+[name_validation_scheme: <legacy | utf8> | default = "legacy"]
+
 resource_monitor:
   # Comma-separated list of resources to monitor. Supported values are cpu and
   # heap, which tracks metrics from github.com/prometheus/procfs and

go.mod

@@ -43,9 +43,9 @@ require (
 	github.com/prometheus/alertmanager v0.28.1
 	github.com/prometheus/client_golang v1.22.0
 	github.com/prometheus/client_model v0.6.2
-	github.com/prometheus/common v0.63.0
+	github.com/prometheus/common v0.65.0
 	// Prometheus maps version 2.x.y to tags v0.x.y.
-	github.com/prometheus/prometheus v0.303.1
+	github.com/prometheus/prometheus v1.99.0
 	github.com/segmentio/fasthash v1.0.3
 	github.com/sony/gobreaker v1.0.0
 	github.com/spf13/afero v1.11.0

go.sum

@@ -838,8 +838,8 @@ github.com/prometheus/common v0.4.1/go.mod h1:TNfzLD0ON7rHzMJeJkieUDPYmFC7Snx/y8
 github.com/prometheus/common v0.9.1/go.mod h1:yhUN8i9wzaXS3w1O07YhxHEBxD+W35wd8bs7vj7HSQ4=
 github.com/prometheus/common v0.10.0/go.mod h1:Tlit/dnDKsSWFlCLTWaA1cyBgKHSMdTB80sz/V91rCo=
 github.com/prometheus/common v0.26.0/go.mod h1:M7rCNAaPfAosfx8veZJCuw84e35h3Cfd9VFqTh1DIvc=
-github.com/prometheus/common v0.63.0 h1:YR/EIY1o3mEFP/kZCD7iDMnLPlGyuU2Gb3HIcXnA98k=
-github.com/prometheus/common v0.63.0/go.mod h1:VVFF/fBIoToEnWRVkYoXEkq3R3paCoxG9PXP74SnV18=
+github.com/prometheus/common v0.65.0 h1:QDwzd+G1twt//Kwj/Ww6E9FQq1iVMmODnILtW1t2VzE=
+github.com/prometheus/common v0.65.0/go.mod h1:0gZns+BLRQ3V6NdaerOhMbwwRbNh9hkGINtQAsP5GS8=
 github.com/prometheus/exporter-toolkit v0.14.0 h1:NMlswfibpcZZ+H0sZBiTjrA3/aBFHkNZqE+iCj5EmRg=
 github.com/prometheus/exporter-toolkit v0.14.0/go.mod h1:Gu5LnVvt7Nr/oqTBUC23WILZepW0nffNo10XdhQcwWA=
 github.com/prometheus/procfs v0.0.0-20181005140218-185b4288413d/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk=

pkg/cortex/cortex.go

@@ -14,6 +14,8 @@ import (
 	"github.com/go-kit/log/level"
 	"github.com/pkg/errors"
 	"github.com/prometheus/client_golang/prometheus"
+	"github.com/prometheus/common/model"
+	prom_config "github.com/prometheus/prometheus/config"
 	"github.com/prometheus/prometheus/promql"
 	prom_storage "github.com/prometheus/prometheus/storage"
 	"github.com/weaveworks/common/server"
@@ -90,11 +92,12 @@ var (
 
 // Config is the root config for Cortex.
 type Config struct {
-	Target          flagext.StringSliceCSV  `yaml:"target"`
-	AuthEnabled     bool                    `yaml:"auth_enabled"`
-	PrintConfig     bool                    `yaml:"-"`
-	HTTPPrefix      string                  `yaml:"http_prefix"`
-	ResourceMonitor configs.ResourceMonitor `yaml:"resource_monitor"`
+	Target               flagext.StringSliceCSV  `yaml:"target"`
+	AuthEnabled          bool                    `yaml:"auth_enabled"`
+	PrintConfig          bool                    `yaml:"-"`
+	HTTPPrefix           string                  `yaml:"http_prefix"`
+	ResourceMonitor      configs.ResourceMonitor `yaml:"resource_monitor"`
+	NameValidationScheme string                  `yaml:"name_validation_scheme"`
 
 	ExternalQueryable prom_storage.Queryable `yaml:"-"`
 	ExternalPusher    ruler.Pusher           `yaml:"-"`
@@ -146,7 +149,7 @@ func (c *Config) RegisterFlags(f *flag.FlagSet) {
 	f.BoolVar(&c.AuthEnabled, "auth.enabled", true, "Set to false to disable auth.")
 	f.BoolVar(&c.PrintConfig, "print.config", false, "Print the config and exit.")
 	f.StringVar(&c.HTTPPrefix, "http.prefix", "/api/prom", "HTTP path prefix for Cortex API.")
-
+	f.StringVar(&c.NameValidationScheme, "name.validation_scheme", "legacy", "Validation scheme for metric and label names. Set to utf8 to allow UTF-8 characters.")
 	c.API.RegisterFlags(f)
 	c.registerServerFlagsWithChangedDefaultValues(f)
 	c.Distributor.RegisterFlags(f)
@@ -181,6 +184,11 @@ func (c *Config) RegisterFlags(f *flag.FlagSet) {
 // Validate the cortex config and returns an error if the validation
 // doesn't pass
 func (c *Config) Validate(log log.Logger) error {
+	if c.NameValidationScheme != "" &&
+		c.NameValidationScheme != prom_config.LegacyValidationConfig &&
+		c.NameValidationScheme != prom_config.UTF8ValidationConfig {
+		return fmt.Errorf("invalid name validation scheme: %s", c.NameValidationScheme)
+	}
 	if err := c.validateYAMLEmptyNodes(); err != nil {
 		return err
 	}
@@ -349,7 +357,14 @@ func New(cfg Config) (*Cortex, error) {
 		}
 		os.Exit(0)
 	}
-
+	switch cfg.NameValidationScheme {
+	case "", prom_config.LegacyValidationConfig:
+		model.NameValidationScheme = model.LegacyValidation
+	case prom_config.UTF8ValidationConfig:
+		model.NameValidationScheme = model.UTF8Validation
+	default:
+		return nil, fmt.Errorf("invalid name validation scheme")
+	}
 	// Swap out the default resolver to support multiple tenant IDs separated by a '|'
 	if cfg.TenantFederation.Enabled {
 		util_log.WarnExperimentalUse("tenant-federation")

pkg/cortex/cortex_test.go

@@ -14,6 +14,7 @@ import (
 	"time"
 
 	"github.com/prometheus/client_golang/prometheus"
+	prom_config "github.com/prometheus/prometheus/config"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	"github.com/weaveworks/common/server"
@@ -217,6 +218,42 @@ func TestConfigValidation(t *testing.T) {
 			},
 			expectedError: nil,
 		},
+		{
+			name: "should not fail validation for empty name validation scheme (use legacy by default)",
+			getTestConfig: func() *Config {
+				configuration := newDefaultConfig()
+				configuration.NameValidationScheme = ""
+				return configuration
+			},
+			expectedError: nil,
+		},
+		{
+			name: "should not fail validation for legacy name validation scheme",
+			getTestConfig: func() *Config {
+				configuration := newDefaultConfig()
+				configuration.NameValidationScheme = prom_config.LegacyValidationConfig
+				return configuration
+			},
+			expectedError: nil,
+		},
+		{
+			name: "should not fail validation for utf-8 name validation scheme",
+			getTestConfig: func() *Config {
+				configuration := newDefaultConfig()
+				configuration.NameValidationScheme = prom_config.UTF8ValidationConfig
+				return configuration
+			},
+			expectedError: nil,
+		},
+		{
+			name: "should fail validation for invalid name validation scheme",
+			getTestConfig: func() *Config {
+				configuration := newDefaultConfig()
+				configuration.NameValidationScheme = "invalid"
+				return configuration
+			},
+			expectedError: fmt.Errorf("invalid name validation scheme"),
+		},
 	} {
 		t.Run(tc.name, func(t *testing.T) {
 			err := tc.getTestConfig().Validate(nil)