Address feedback

Signed-off-by: Goutham Veeramachaneni <gouthamve@gmail.com>

CHANGELOG.md

@@ -12,6 +12,7 @@
 * [CHANGE] Experimental Delete Series: `/api/v1/admin/tsdb/delete_series` and `/api/v1/admin/tsdb/cancel_delete_request` purger APIs to return status code `204` instead of `200` for success. #2946
 * [CHANGE] Histogram `cortex_memcache_request_duration_seconds` `method` label value changes from `Memcached.Get` to `Memcached.GetBatched` for batched lookups, and is not reported for non-batched lookups (label value `Memcached.GetMulti` remains, and had exactly the same value as `Get` in nonbatched lookups).  The same change applies to tracing spans. #3046
 * [CHANGE] TLS server validation is now enabled by default, a new parameter `tls_insecure_skip_verify` can be set to true to skip validation optionally. #3030
+* [CHANGE] `cortex_ruler_config_update_failures_total` has been removed in favor of `cortex_ruler_config_last_reload_successful`. #3056
 * [ENHANCEMENT] Add support for azure storage in China, German and US Government environments. #2988
 * [ENHANCEMENT] Query-tee: added a small tolerance to floating point sample values comparison. #2994
 * [ENHANCEMENT] Query-tee: add support for doing a passthrough of requests to preferred backend for unregistered routes #3018

pkg/ruler/manager.go

@@ -20,24 +20,6 @@ import (
 	"github.com/cortexproject/cortex/pkg/util"
 )
 
-var (
-	configUpdatesTotal = promauto.NewCounterVec(prometheus.CounterOpts{
-		Namespace: "cortex",
-		Name:      "ruler_config_updates_total",
-		Help:      "Total number of config updates triggered by a user",
-	}, []string{"user"})
-	configUpdateFailuresTotal = promauto.NewCounterVec(prometheus.CounterOpts{
-		Namespace: "cortex",
-		Name:      "ruler_config_update_failures_total",
-		Help:      "Total number of config update failures triggered by a user",
-	}, []string{"user", "reason"})
-	userManagerFailed = promauto.NewGaugeVec(prometheus.GaugeOpts{
-		Namespace: "cortex",
-		Name:      "ruler_manager_failed",
-		Help:      "Boolean set to 1 whenever the Ruler manager failed to start for a user.",
-	}, []string{"user"})
-)
-
 type DefaultMultiTenantManager struct {
 	cfg            Config
 	notifierCfg    *config.Config
@@ -55,9 +37,12 @@ type DefaultMultiTenantManager struct {
 	notifiersMtx sync.Mutex
 	notifiers    map[string]*rulerNotifier
 
-	managersTotal prometheus.Gauge
-	registry      prometheus.Registerer
-	logger        log.Logger
+	managersTotal                 prometheus.Gauge
+	lastReloadSuccessful          *prometheus.GaugeVec
+	lastReloadSuccessfulTimestamp *prometheus.GaugeVec
+	configUpdatesTotal            *prometheus.CounterVec
+	registry                      prometheus.Registerer
+	logger                        log.Logger
 }
 
 func NewDefaultMultiTenantManager(cfg Config, managerFactory ManagerFactory, reg prometheus.Registerer, logger log.Logger) (*DefaultMultiTenantManager, error) {
@@ -84,6 +69,21 @@ func NewDefaultMultiTenantManager(cfg Config, managerFactory ManagerFactory, reg
 			Name:      "ruler_managers_total",
 			Help:      "Total number of managers registered and running in the ruler",
 		}),
+		lastReloadSuccessful: promauto.With(reg).NewGaugeVec(prometheus.GaugeOpts{
+			Namespace: "cortex",
+			Name:      "ruler_config_last_reload_successful",
+			Help:      "Boolean set to 1 whenever the last configuration reload attempt was successful.",
+		}, []string{"user"}),
+		lastReloadSuccessfulTimestamp: promauto.With(reg).NewGaugeVec(prometheus.GaugeOpts{
+			Namespace: "cortex",
+			Name:      "ruler_config_last_reload_successful_seconds",
+			Help:      "Timestamp of the last successful configuration reload.",
+		}, []string{"user"}),
+		configUpdatesTotal: promauto.With(reg).NewCounterVec(prometheus.CounterOpts{
+			Namespace: "cortex",
+			Name:      "ruler_config_updates_total",
+			Help:      "Total number of config updates triggered by a user",
+		}, []string{"user"}),
 		registry: reg,
 		logger:   logger,
 	}, nil
@@ -104,6 +104,9 @@ func (r *DefaultMultiTenantManager) SyncRuleGroups(ctx context.Context, ruleGrou
 		if _, exists := ruleGroups[userID]; !exists {
 			go mngr.Stop()
 			delete(r.userManagers, userID)
+			r.lastReloadSuccessful.DeleteLabelValues(userID)
+			r.lastReloadSuccessfulTimestamp.DeleteLabelValues(userID)
+			r.configUpdatesTotal.DeleteLabelValues(userID)
 			level.Info(r.logger).Log("msg", "deleting rule manager", "user", userID)
 		}
 	}
@@ -118,19 +121,19 @@ func (r *DefaultMultiTenantManager) syncRulesToManager(ctx context.Context, user
 	// have been updated
 	update, files, err := r.mapper.MapRules(user, groups.Formatted())
 	if err != nil {
+		r.lastReloadSuccessful.WithLabelValues(user).Set(0)
 		level.Error(r.logger).Log("msg", "unable to map rule files", "user", user, "err", err)
 		return
 	}
 
 	if update {
 		level.Debug(r.logger).Log("msg", "updating rules", "user", "user")
-		configUpdatesTotal.WithLabelValues(user).Inc()
+		r.configUpdatesTotal.WithLabelValues(user).Inc()
 		manager, exists := r.userManagers[user]
 		if !exists {
 			manager, err = r.newManager(ctx, user)
 			if err != nil {
-				configUpdateFailuresTotal.WithLabelValues(user, "rule-manager-creation-failure").Inc()
-				userManagerFailed.WithLabelValues(user).Set(1)
+				r.lastReloadSuccessful.WithLabelValues(user).Set(0)
 				level.Error(r.logger).Log("msg", "unable to create rule manager", "user", user, "err", err)
 				return
 			}
@@ -141,13 +144,13 @@ func (r *DefaultMultiTenantManager) syncRulesToManager(ctx context.Context, user
 		}
 		err = manager.Update(r.cfg.EvaluationInterval, files, nil)
 		if err != nil {
-			configUpdateFailuresTotal.WithLabelValues(user, "rules-update-failure").Inc()
-			userManagerFailed.WithLabelValues(user).Set(1)
+			r.lastReloadSuccessful.WithLabelValues(user).Set(0)
 			level.Error(r.logger).Log("msg", "unable to update rule manager", "user", user, "err", err)
 			return
 		}
 
-		userManagerFailed.WithLabelValues(user).Set(0)
+		r.lastReloadSuccessful.WithLabelValues(user).Set(1)
+		r.lastReloadSuccessfulTimestamp.WithLabelValues(user).SetToCurrentTime()
 	}
 }