feat(operator): make the reconcile resync interval configurable

README.md

@@ -14,6 +14,7 @@ Redis Operator creates/configures/manages redis-failovers atop Kubernetes.
   - [Using kustomize](#using-kustomize)
 - [Usage](#usage)
   - [Reducing update churn (`--enable-hash`)](#reducing-update-churn---enable-hash)
+  - [Reconcile interval (`--resync-period`)](#reconcile-interval---resync-period)
   - [Persistence](#persistence)
   - [NodeAffinity and Tolerations](#nodeaffinity-and-tolerations)
 - [Topology Spread Contraints](#topology-spread-contraints)
@@ -166,6 +167,13 @@ sync, because the operator's *desired* object is unchanged and so its hash still
 trading the operator's self-healing of manual drift for far fewer API writes. The flag is **off by
 default**, so upgrading changes nothing until you opt in.
 
+### Reconcile interval (`--resync-period`)
+
+Beyond reacting to change events, the operator re-reconciles every `RedisFailover` on a fixed
+interval so it can recover from missed events and correct drift. This defaults to `30s` and can be
+tuned with `--resync-period` (any Go duration, e.g. `--resync-period=1m`). Larger values reduce API
+load at the cost of slower periodic healing; smaller values react faster but poll more often.
+
 ### Persistence
 
 The operator has the ability of add persistence to Redis data. By default an `emptyDir` will be used, so the data is not saved.

cmd/utils/flags.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"path/filepath"
 	"regexp"
+	"time"
 
 	"github.com/dnse-tech/redis-operator/operator/redisfailover"
 	"k8s.io/client-go/util/homedir"
@@ -23,6 +24,7 @@ type CMDFlags struct {
 	Concurrency              int
 	LogLevel                 string
 	EnableObjectHashing      bool
+	ResyncPeriod             time.Duration
 }
 
 // Init initializes and parse the flags
@@ -43,6 +45,7 @@ func (c *CMDFlags) Init() {
 	// Off by default: skipping unchanged writes also stops the operator from
 	// correcting resources edited by hand, so opting in is a deliberate choice.
 	flag.BoolVar(&c.EnableObjectHashing, "enable-hash", false, "Skip updating owned resources when they already match the desired state")
+	flag.DurationVar(&c.ResyncPeriod, "resync-period", 30*time.Second, "How often every RedisFailover is re-reconciled even without a change event")
 	// Parse flags
 	flag.Parse()
 
@@ -58,5 +61,6 @@ func (c *CMDFlags) ToRedisOperatorConfig() redisfailover.Config {
 		MetricsPath:              c.MetricsPath,
 		Concurrency:              c.Concurrency,
 		SupportedNamespacesRegex: c.SupportedNamespacesRegex,
+		ResyncPeriod:             c.ResyncPeriod,
 	}
 }

operator/redisfailover/config.go

@@ -1,9 +1,14 @@
 package redisfailover
 
+import "time"
+
 // Config is the configuration for the redis operator.
 type Config struct {
 	ListenAddress            string
 	MetricsPath              string
 	Concurrency              int
 	SupportedNamespacesRegex string
+	// ResyncPeriod is how often every RedisFailover is re-reconciled even
+	// without a change event. Zero falls back to the built-in default.
+	ResyncPeriod time.Duration
 }

operator/redisfailover/factory.go

@@ -23,9 +23,9 @@ import (
 )
 
 const (
-	resync       = 30 * time.Second
-	operatorName = "redis-operator"
-	lockKey      = "redis-failover-lease"
+	defaultResync = 30 * time.Second
+	operatorName  = "redis-operator"
+	lockKey       = "redis-failover-lease"
 )
 
 // New will create an operator that is responsible of managing all the required stuff
@@ -40,6 +40,11 @@ func New(cfg Config, k8sService k8s.Services, k8sClient kubernetes.Interface, lo
 	rfHandler := NewRedisFailoverHandler(cfg, rfService, rfChecker, rfHealer, k8sService, kooperMetricsRecorder, logger)
 	rfRetriever := NewRedisFailoverRetriever(cfg, k8sService)
 
+	resync := cfg.ResyncPeriod
+	if resync <= 0 {
+		resync = defaultResync
+	}
+
 	kooperLogger := kooperlogger{Logger: logger.WithField("operator", "redisfailover")}
 	// Leader election service.
 	leSVC, err := leaderelection.NewDefault(lockKey, lockNamespace, k8sClient, kooperLogger)