feat: support configurable name validation (legacy or UTF-8 schemes)

Signed-off-by: 7h3-3mp7y-m4n <emailtorash@gmail.com>

Author: 7h3-3mp7y-m4n

CHANGELOG.md

@@ -20,6 +20,7 @@
 * [FEATURE] Compactor: Add support for percentage based sharding for compactors. #6738
 * [FEATURE] Querier: Allow choosing PromQL engine via header. #6777
 * [FEATURE] Querier: Support for configuring query optimizers and enabling XFunctions in the Thanos engine. #6873
+*[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`)
 * [ENHANCEMENT] Tenant Federation: Add a # of query result limit logic when the `-tenant-federation.regex-matcher-enabled` is enabled. #6845
 * [ENHANCEMENT] Query Frontend: Add a `cortex_slow_queries_total` metric to track # of slow queries per user. #6859
 * [ENHANCEMENT] Query Frontend: Change to return 400 when the tenant resolving fail. #6715

docs/configuration/config-file-reference.md

@@ -68,6 +68,10 @@ Where default_value is the value to use if the environment variable is undefined
 # CLI flag: -http.prefix
 [http_prefix: <string> | default = "/api/prom"]
 
+# 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

@@ -45,7 +45,7 @@ require (
 	github.com/prometheus/client_model v0.6.2
 	github.com/prometheus/common v0.63.0
 	// 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

pkg/cortex/configinit/init.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"
@@ -31,7 +33,6 @@ import (
 	"github.com/cortexproject/cortex/pkg/configs"
 	configAPI "github.com/cortexproject/cortex/pkg/configs/api"
 	"github.com/cortexproject/cortex/pkg/configs/db"
-	_ "github.com/cortexproject/cortex/pkg/cortex/configinit"
 	"github.com/cortexproject/cortex/pkg/cortex/storage"
 	"github.com/cortexproject/cortex/pkg/cortexpb"
 	"github.com/cortexproject/cortex/pkg/distributor"
@@ -90,11 +91,12 @@ 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:"-"`
@@ -146,6 +148,7 @@ 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)
@@ -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 {
+	switch c.NameValidationScheme {
+	case "", prom_config.LegacyValidationConfig, prom_config.UTF8ValidationConfig:
+	default:
+		return fmt.Errorf("invalid name validation scheme: %s", c.NameValidationScheme)
+	}
 	if err := c.validateYAMLEmptyNodes(); err != nil {
 		return err
 	}
@@ -349,7 +357,12 @@ func New(cfg Config) (*Cortex, error) {
 		}
 		os.Exit(0)
 	}
-
+	//nolint:staticcheck // SA1019: using deprecated NameValidationScheme intentionally as a temporary compatibility workaround for UTF-8 migration issues
+	if cfg.NameValidationScheme == prom_config.UTF8ValidationConfig {
+		model.NameValidationScheme = model.UTF8Validation
+	} else {
+		model.NameValidationScheme = model.LegacyValidation
+	}
 	// 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.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)

pkg/cortex/cortex_test.go

@@ -35,7 +35,6 @@ import (
 	"google.golang.org/grpc/status"
 
 	promchunk "github.com/cortexproject/cortex/pkg/chunk/encoding"
-	_ "github.com/cortexproject/cortex/pkg/cortex/configinit"
 	"github.com/cortexproject/cortex/pkg/cortexpb"
 	"github.com/cortexproject/cortex/pkg/ha"
 	"github.com/cortexproject/cortex/pkg/ingester"

pkg/distributor/distributor_test.go

@@ -5,6 +5,8 @@ import (
 	"strings"
 	"testing"
 
+	"github.com/cortexproject/cortex/pkg/cortexpb"
+	util_log "github.com/cortexproject/cortex/pkg/util/log"
 	"github.com/go-kit/log"
 	"github.com/prometheus/client_golang/prometheus"
 	"github.com/prometheus/client_golang/prometheus/testutil"
@@ -15,10 +17,6 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	"github.com/weaveworks/common/httpgrpc"
-
-	_ "github.com/cortexproject/cortex/pkg/cortex/configinit"
-	"github.com/cortexproject/cortex/pkg/cortexpb"
-	util_log "github.com/cortexproject/cortex/pkg/util/log"
 )
 
 func TestValidateLabels(t *testing.T) {