Merge branch 'master' into check-cluster-UID

Makefile

@@ -78,6 +78,9 @@ $(GENERATED_CRDS): $(GENERATED)
 local: ${SOURCES} $(GENERATED_CRDS)
 	CGO_ENABLED=${CGO_ENABLED} go build -o build/${BINARY} $(LOCAL_BUILD_FLAGS) -ldflags "$(LDFLAGS)" $(SOURCES)
 
+wasm: ${SOURCES} $(GENERATED_CRDS)
+	GOOS=wasip1 GOARCH=wasm CGO_ENABLED=${CGO_ENABLED} go build -o build/${BINARY}.wasm ${BUILD_FLAGS} -ldflags "$(LDFLAGS)" $(SOURCES)
+
 linux: ${SOURCES} $(GENERATED_CRDS)
 	GOOS=linux GOARCH=amd64 CGO_ENABLED=${CGO_ENABLED} go build -o build/linux/${BINARY} ${BUILD_FLAGS} -ldflags "$(LDFLAGS)" $(SOURCES)
 

charts/postgres-operator/crds/operatorconfigurations.yaml

@@ -79,6 +79,9 @@ spec:
               enable_lazy_spilo_upgrade:
                 type: boolean
                 default: false
+              enable_maintenance_windows:
+                type: boolean
+                default: true
               enable_pgversion_env_var:
                 type: boolean
                 default: true

charts/postgres-operator/values.yaml

@@ -27,6 +27,8 @@ configGeneral:
   - "all"
   # update only the statefulsets without immediately doing the rolling update
   enable_lazy_spilo_upgrade: false
+  # toogle to use maintenance windows feature
+  enable_maintenance_windows: true
   # set the PGVERSION env var instead of providing the version via postgresql.bin_dir in SPILO_CONFIGURATION
   enable_pgversion_env_var: true
   # start any new database pod without limitations on shm memory

docs/administrator.md

@@ -65,7 +65,10 @@ the `PGVERSION` environment variable is set for the database pods. Since
 In-place major version upgrades can be configured to be executed by the
 operator with the `major_version_upgrade_mode` option. By default, it is
 enabled (mode: `manual`). In any case, altering the version in the manifest
-will trigger a rolling update of pods to update the `PGVERSION` env variable.
+will update the desired `PGVERSION`. If `maintenanceWindows` are configured,
+major-version-related pod rotation is deferred until the next maintenance
+window. Without maintenance windows, the operator will trigger a rolling
+update of pods to apply the new `PGVERSION`.
 Spilo's [`configure_spilo`](https://github.com/zalando/spilo/blob/master/postgres-appliance/scripts/configure_spilo.py)
 script will notice the version mismatch but start the current version again.
 
@@ -92,10 +95,11 @@ Thus, the `full` mode can create drift between desired and actual state.
 
 ### Upgrade during maintenance windows
 
-When `maintenanceWindows` are defined in the Postgres manifest the operator
-will trigger a major version upgrade only during these periods. Make sure they
-are at least twice as long as your configured `resync_period` to guarantee
-that operator actions can be triggered.
+When `maintenanceWindows` are defined in the Postgres manifest or in the global
+config the operator will trigger major-version-related pod rotation and the
+major version upgrade only during these periods. Make sure they are at least
+twice as long as your configured `resync_period` to guarantee that operator
+actions can be triggered.
 
 ### Upgrade annotations
 

docs/reference/cluster_manifest.md

@@ -118,7 +118,9 @@ These parameters are grouped directly under  the `spec` key in the manifest.
   a list which defines specific time frames when certain maintenance operations
   such as automatic major upgrades or master pod migration are allowed to happen.
   Accepted formats are "01:00-06:00" for daily maintenance windows or
-  "Sat:00:00-04:00" for specific days, with all times in UTC.
+  "Sat:00:00-04:00" for specific days, with all times in UTC. Note, when the
+  global config option `enable_maintenance_windows` is false, the specified
+  windows will be ignored.
 
 * **users**
   a map of usernames to user flags for the users that should be created in the

docs/reference/operator_parameters.md

@@ -173,6 +173,9 @@ Those are top-level keys, containing both leaf keys and groups.
   the thresholds. The value must be `"true"` to be effective. The default is empty
   which means the feature is disabled.
 
+* **enable_maintenance_windows**
+  toggle for using the maintenance windows feature. Default is `"true"`.
+
 * **maintenance_windows**
   a list which defines specific time frames when certain maintenance
   operations such as automatic major upgrades or master pod migration are

e2e/run.sh

@@ -14,6 +14,13 @@ readonly e2e_test_runner_image="ghcr.io/zalando/postgres-operator-e2e-tests-runn
 export GOPATH=${GOPATH-~/go}
 export PATH=${GOPATH}/bin:$PATH
 
+# detect system architecture for pulling the correct Spilo image
+case "$(uname -m)" in
+    x86_64)  readonly PLATFORM="linux/amd64" ;;
+    aarch64|arm64) readonly PLATFORM="linux/arm64" ;;
+    *) echo "Unsupported architecture: $(uname -m)"; exit 1 ;;
+esac
+
 echo "Clustername: ${cluster_name}"
 echo "Kubeconfig path: ${kubeconfig_path}"
 
@@ -43,9 +50,8 @@ function start_kind(){
   export KUBECONFIG="${kubeconfig_path}"
   kind create cluster --name ${cluster_name} --config kind-cluster-postgres-operator-e2e-tests.yaml  
   
-  # Pull all platforms to satisfy Kind's --all-platforms requirement
-  docker pull --platform linux/amd64 "${spilo_image}"
-  docker pull --platform linux/arm64 "${spilo_image}"
+  echo "Pulling Spilo image for platform ${PLATFORM}"
+  docker pull --platform ${PLATFORM} "${spilo_image}"
   kind load docker-image "${spilo_image}" --name ${cluster_name}
 }
 

go.mod

@@ -6,11 +6,11 @@ require (
 	github.com/Masterminds/semver v1.5.0
 	github.com/aws/aws-sdk-go v1.55.8
 	github.com/golang/mock v1.6.0
-	github.com/lib/pq v1.10.9
+	github.com/lib/pq v1.11.2
 	github.com/motomux/pretty v0.0.0-20161209205251-b2aad2c9a95d
 	github.com/pkg/errors v0.9.1
 	github.com/r3labs/diff v1.1.0
-	github.com/sirupsen/logrus v1.9.3
+	github.com/sirupsen/logrus v1.9.4
 	github.com/stretchr/testify v1.11.1
 	golang.org/x/crypto v0.45.0
 	gopkg.in/yaml.v2 v2.4.0

go.sum

@@ -73,6 +73,8 @@ github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/lib/pq v1.10.9 h1:YXG7RB+JIjhP29X+OtkiDnYaXQwpS4JEWq7dtCCRUEw=
 github.com/lib/pq v1.10.9/go.mod h1:AlVN5x4E4T544tWzH6hKfbfQvm3HdbOxrmggDNAPY9o=
+github.com/lib/pq v1.11.2 h1:x6gxUeu39V0BHZiugWe8LXZYZ+Utk7hSJGThs8sdzfs=
+github.com/lib/pq v1.11.2/go.mod h1:/p+8NSbOcwzAEI7wiMXFlgydTwcgTr3OSKMsD2BitpA=
 github.com/mailru/easyjson v0.7.7 h1:UGYAvKxe3sBsEDzO8ZeWOSlIQfWFlxbzLZe7hwFURr0=
 github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=
 github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA=
@@ -113,6 +115,8 @@ github.com/rogpeppe/go-internal v1.12.0/go.mod h1:E+RYuTGaKKdloAfM02xzb0FW3Paa99
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/sirupsen/logrus v1.9.3 h1:dueUQJ1C2q9oE3F7wvmSGAaVtTmUizReu6fjN8uqzbQ=
 github.com/sirupsen/logrus v1.9.3/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
+github.com/sirupsen/logrus v1.9.4 h1:TsZE7l11zFCLZnZ+teH4Umoq5BhEIfIzfRDZ1Uzql2w=
+github.com/sirupsen/logrus v1.9.4/go.mod h1:ftWc9WdOfJ0a92nsE2jF5u5ZwH8Bv2zdeOC42RjbV2g=
 github.com/spf13/cobra v1.9.1 h1:CXSaggrXdbHK9CF+8ywj8Amf7PBRmPCOJugH954Nnlo=
 github.com/spf13/cobra v1.9.1/go.mod h1:nDyEzZ8ogv936Cinf6g1RU9MRY64Ir93oCnqb9wxYW0=
 github.com/spf13/pflag v1.0.6 h1:jFzHGLGAlb3ruxLB8MhbI6A8+AQX/2eW4qeyNZXNp2o=

hack/update-codegen.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 # Copyright 2017 The Kubernetes Authors.
 #

manifests/configmap.yaml

@@ -46,6 +46,7 @@ data:
   enable_ebs_gp3_migration_max_size: "1000"
   enable_init_containers: "true"
   enable_lazy_spilo_upgrade: "false"
+  enable_maintenance_windows: "true"
   enable_master_load_balancer: "false"
   enable_master_pooler_load_balancer: "false"
   enable_password_rotation: "false"

manifests/operatorconfiguration.crd.yaml

@@ -77,6 +77,9 @@ spec:
               enable_lazy_spilo_upgrade:
                 type: boolean
                 default: false
+              enable_maintenance_windows:
+                type: boolean
+                default: true
               enable_pgversion_env_var:
                 type: boolean
                 default: true

manifests/postgresql-operator-default-configuration.yaml

@@ -8,6 +8,7 @@ configuration:
   # crd_categories:
   # - all
   # enable_lazy_spilo_upgrade: false
+  enable_maintenance_windows: true
   enable_pgversion_env_var: true
   # enable_shm_volume: true
   enable_spilo_wal_path_compat: false

pkg/apis/acid.zalan.do/v1/crds.go

@@ -105,6 +105,9 @@ var OperatorConfigCRDResourceValidation = apiextv1.CustomResourceValidation{
 					"enable_lazy_spilo_upgrade": {
 						Type: "boolean",
 					},
+					"enable_maintenance_windows": {
+						Type: "boolean",
+					},
 					"enable_shm_volume": {
 						Type: "boolean",
 					},

pkg/apis/acid.zalan.do/v1/operator_configuration_type.go

@@ -266,6 +266,7 @@ type OperatorConfigurationData struct {
 	Workers                       uint32                             `json:"workers,omitempty"`
 	ResyncPeriod                  Duration                           `json:"resync_period,omitempty"`
 	RepairPeriod                  Duration                           `json:"repair_period,omitempty"`
+	EnableMaintenanceWindows      *bool                              `json:"enable_maintenance_windows,omitempty"`
 	MaintenanceWindows            []MaintenanceWindow                `json:"maintenance_windows,omitempty"`
 	SetMemoryRequestToLimit       bool                               `json:"set_memory_request_to_limit,omitempty"`
 	ShmVolume                     *bool                              `json:"enable_shm_volume,omitempty"`

pkg/apis/acid.zalan.do/v1/zz_generated.deepcopy.go

@@ -433,6 +433,11 @@ func (in *OperatorConfigurationData) DeepCopyInto(out *OperatorConfigurationData
 		*out = make([]string, len(*in))
 		copy(*out, *in)
 	}
+	if in.EnableMaintenanceWindows != nil {
+		in, out := &in.EnableMaintenanceWindows, &out.EnableMaintenanceWindows
+		*out = new(bool)
+		**out = **in
+	}
 	if in.MaintenanceWindows != nil {
 		in, out := &in.MaintenanceWindows, &out.MaintenanceWindows
 		*out = make([]MaintenanceWindow, len(*in))

pkg/cluster/cluster.go

@@ -1784,7 +1784,20 @@ func (c *Cluster) GetSwitchoverSchedule() string {
 func (c *Cluster) getSwitchoverScheduleAtTime(now time.Time) string {
 	var possibleSwitchover, schedule time.Time
 
-	for _, window := range c.Spec.MaintenanceWindows {
+	maintenanceWindows := c.Spec.MaintenanceWindows
+	if len(maintenanceWindows) == 0 {
+		maintenanceWindows = make([]acidv1.MaintenanceWindow, 0, len(c.OpConfig.MaintenanceWindows))
+		for _, windowStr := range c.OpConfig.MaintenanceWindows {
+			var window acidv1.MaintenanceWindow
+			if err := window.UnmarshalJSON([]byte(windowStr)); err != nil {
+				c.logger.Errorf("could not parse default maintenance window %q: %v", windowStr, err)
+				continue
+			}
+			maintenanceWindows = append(maintenanceWindows, window)
+		}
+	}
+
+	for _, window := range maintenanceWindows {
 		// in the best case it is possible today
 		possibleSwitchover = time.Date(now.Year(), now.Month(), now.Day(), window.StartTime.Hour(), window.StartTime.Minute(), 0, 0, time.UTC)
 		if window.Everyday {
@@ -1806,6 +1819,11 @@ func (c *Cluster) getSwitchoverScheduleAtTime(now time.Time) string {
 			schedule = possibleSwitchover
 		}
 	}
+
+	if schedule.IsZero() {
+		return ""
+	}
+
 	return schedule.Format("2006-01-02T15:04+00")
 }
 

pkg/cluster/cluster_test.go

@@ -2125,10 +2125,13 @@ func TestGetSwitchoverSchedule(t *testing.T) {
 	pastWindowTimeStart := pastTimeStart.Format("15:04")
 	pastWindowTimeEnd := now.Add(-1 * time.Hour).Format("15:04")
 
+	defaultWindowStr := fmt.Sprintf("%s-%s", futureWindowTimeStart, futureWindowTimeEnd)
+
 	tests := []struct {
-		name     string
-		windows  []acidv1.MaintenanceWindow
-		expected string
+		name           string
+		windows        []acidv1.MaintenanceWindow
+		defaultWindows []string
+		expected       string
 	}{
 		{
 			name: "everyday maintenance windows is later today",
@@ -2190,11 +2193,40 @@ func TestGetSwitchoverSchedule(t *testing.T) {
 			},
 			expected: pastTimeStart.AddDate(0, 0, 1).Format("2006-01-02T15:04+00"),
 		},
+		{
+			name:           "fallback to operator default window when spec is empty",
+			windows:        []acidv1.MaintenanceWindow{},
+			defaultWindows: []string{defaultWindowStr},
+			expected:       futureTimeStart.Format("2006-01-02T15:04+00"),
+		},
+		{
+			name:           "no windows defined returns empty string",
+			windows:        []acidv1.MaintenanceWindow{},
+			defaultWindows: nil,
+			expected:       "",
+		},
+		{
+			name: "choose the earliest window from multiple in spec",
+			windows: []acidv1.MaintenanceWindow{
+				{
+					Weekday:   now.AddDate(0, 0, 2).Weekday(),
+					StartTime: mustParseTime(futureWindowTimeStart),
+					EndTime:   mustParseTime(futureWindowTimeEnd),
+				},
+				{
+					Weekday:   now.AddDate(0, 0, 1).Weekday(),
+					StartTime: mustParseTime(pastWindowTimeStart),
+					EndTime:   mustParseTime(pastWindowTimeEnd),
+				},
+			},
+			expected: pastTimeStart.AddDate(0, 0, 1).Format("2006-01-02T15:04+00"),
+		},
 	}
 
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			cluster.Spec.MaintenanceWindows = tt.windows
+			cluster.OpConfig.MaintenanceWindows = tt.defaultWindows
 			schedule := cluster.getSwitchoverScheduleAtTime(now)
 			if schedule != tt.expected {
 				t.Errorf("Expected GetSwitchoverSchedule to return %s, returned: %s", tt.expected, schedule)

pkg/cluster/sync.go

@@ -41,6 +41,12 @@ func (c *Cluster) Sync(newSpec *acidv1.Postgresql) error {
 	defer c.mu.Unlock()
 
 	oldSpec := c.Postgresql
+
+	if !c.isInMaintenanceWindow(newSpec.Spec.MaintenanceWindows) {
+		// do not apply any major version related changes yet
+		newSpec.Spec.PostgresqlParam.PgVersion = oldSpec.Spec.PostgresqlParam.PgVersion
+	}
+
 	c.setSpec(newSpec)
 
 	defer func() {
@@ -97,11 +103,6 @@ func (c *Cluster) Sync(newSpec *acidv1.Postgresql) error {
 		}
 	}
 
-	if !c.isInMaintenanceWindow(newSpec.Spec.MaintenanceWindows) {
-		// do not apply any major version related changes yet
-		newSpec.Spec.PostgresqlParam.PgVersion = oldSpec.Spec.PostgresqlParam.PgVersion
-	}
-
 	if err = c.syncStatefulSet(); err != nil {
 		if !k8sutil.ResourceAlreadyExists(err) {
 			err = fmt.Errorf("could not sync statefulsets: %v", err)

pkg/cluster/util.go

@@ -675,7 +675,9 @@ func isStandbyCluster(spec *acidv1.PostgresSpec) bool {
 }
 
 func (c *Cluster) isInMaintenanceWindow(specMaintenanceWindows []acidv1.MaintenanceWindow) bool {
-	if len(specMaintenanceWindows) == 0 && len(c.OpConfig.MaintenanceWindows) == 0 {
+	ignoreMaintenanceWindows := c.OpConfig.EnableMaintenanceWindows != nil && !*c.OpConfig.EnableMaintenanceWindows
+	noWindowsDefined := len(specMaintenanceWindows) == 0 && len(c.OpConfig.MaintenanceWindows) == 0
+	if noWindowsDefined || ignoreMaintenanceWindows {
 		return true
 	}
 	now := time.Now()

pkg/cluster/util_test.go

@@ -660,6 +660,7 @@ func TestIsInMaintenanceWindow(t *testing.T) {
 	cluster := New(
 		Config{
 			OpConfig: config.Config{
+				EnableMaintenanceWindows: util.True(),
 				Resources: config.Resources{
 					ClusterLabels:        map[string]string{"application": "spilo"},
 					ClusterNameLabel:     "cluster-name",
@@ -683,12 +684,27 @@ func TestIsInMaintenanceWindow(t *testing.T) {
 		name          string
 		windows       []acidv1.MaintenanceWindow
 		configWindows []string
+		windowsFlag   bool
 		expected      bool
 	}{
 		{
 			name:          "no maintenance windows",
 			windows:       nil,
 			configWindows: nil,
+			windowsFlag:   true,
+			expected:      true,
+		},
+		{
+			name: "maintenance windows diabled",
+			windows: []acidv1.MaintenanceWindow{
+				{
+					Everyday:  true,
+					StartTime: mustParseTime("00:00"),
+					EndTime:   mustParseTime("23:59"),
+				},
+			},
+			configWindows: nil,
+			windowsFlag:   false,
 			expected:      true,
 		},
 		{
@@ -701,6 +717,7 @@ func TestIsInMaintenanceWindow(t *testing.T) {
 				},
 			},
 			configWindows: nil,
+			windowsFlag:   true,
 			expected:      true,
 		},
 		{
@@ -713,6 +730,7 @@ func TestIsInMaintenanceWindow(t *testing.T) {
 				},
 			},
 			configWindows: nil,
+			windowsFlag:   true,
 			expected:      true,
 		},
 		{
@@ -724,24 +742,35 @@ func TestIsInMaintenanceWindow(t *testing.T) {
 					EndTime:   mustParseTime(futureTimeEndFormatted),
 				},
 			},
-			expected: false,
+			windowsFlag: true,
+			expected:    false,
 		},
 		{
 			name:          "global maintenance windows with future interval time",
 			windows:       nil,
 			configWindows: []string{fmt.Sprintf("%s-%s", futureTimeStartFormatted, futureTimeEndFormatted)},
+			windowsFlag:   true,
 			expected:      false,
 		},
 		{
 			name:          "global maintenance windows all day",
 			windows:       nil,
 			configWindows: []string{"00:00-02:00", "02:00-23:59"},
+			windowsFlag:   true,
+			expected:      true,
+		},
+		{
+			name:          "global maintenance windows ignored",
+			windows:       nil,
+			configWindows: []string{"00:00-02:00", "02:00-23:59"},
+			windowsFlag:   false,
 			expected:      true,
 		},
 	}
 
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
+			cluster.OpConfig.EnableMaintenanceWindows = &tt.windowsFlag
 			cluster.OpConfig.MaintenanceWindows = tt.configWindows
 			cluster.Spec.MaintenanceWindows = tt.windows
 			if cluster.isInMaintenanceWindow(cluster.Spec.MaintenanceWindows) != tt.expected {

pkg/controller/operator_config.go

@@ -51,6 +51,7 @@ func (c *Controller) importConfigurationFromCRD(fromCRD *acidv1.OperatorConfigur
 	result.ShmVolume = util.CoalesceBool(fromCRD.ShmVolume, util.True())
 	result.SidecarImages = fromCRD.SidecarImages
 	result.SidecarContainers = fromCRD.SidecarContainers
+	result.EnableMaintenanceWindows = util.CoalesceBool(fromCRD.EnableMaintenanceWindows, util.True())
 	if len(fromCRD.MaintenanceWindows) > 0 {
 		result.MaintenanceWindows = make([]string, 0, len(fromCRD.MaintenanceWindows))
 		for _, window := range fromCRD.MaintenanceWindows {

pkg/util/config/config.go

@@ -173,14 +173,15 @@ type Config struct {
 	LogicalBackup
 	ConnectionPooler
 
-	WatchedNamespace        string            `name:"watched_namespace"` // special values: "*" means 'watch all namespaces', the empty string "" means 'watch a namespace where operator is deployed to'
-	KubernetesUseConfigMaps bool              `name:"kubernetes_use_configmaps" default:"false"`
-	EtcdHost                string            `name:"etcd_host" default:""` // special values: the empty string "" means Patroni will use K8s as a DCS
-	MaintenanceWindows      []string          `name:"maintenance_windows"`
-	DockerImage             string            `name:"docker_image" default:"ghcr.io/zalando/spilo-18:4.1-p1"`
-	SidecarImages           map[string]string `name:"sidecar_docker_images"` // deprecated in favour of SidecarContainers
-	SidecarContainers       []v1.Container    `name:"sidecars"`
-	PodServiceAccountName   string            `name:"pod_service_account_name" default:"postgres-pod"`
+	WatchedNamespace         string            `name:"watched_namespace"` // special values: "*" means 'watch all namespaces', the empty string "" means 'watch a namespace where operator is deployed to'
+	KubernetesUseConfigMaps  bool              `name:"kubernetes_use_configmaps" default:"false"`
+	EtcdHost                 string            `name:"etcd_host" default:""` // special values: the empty string "" means Patroni will use K8s as a DCS
+	EnableMaintenanceWindows *bool             `name:"enable_maintenance_windows" default:"true"`
+	MaintenanceWindows       []string          `name:"maintenance_windows"`
+	DockerImage              string            `name:"docker_image" default:"ghcr.io/zalando/spilo-18:4.1-p1"`
+	SidecarImages            map[string]string `name:"sidecar_docker_images"` // deprecated in favour of SidecarContainers
+	SidecarContainers        []v1.Container    `name:"sidecars"`
+	PodServiceAccountName    string            `name:"pod_service_account_name" default:"postgres-pod"`
 	// value of this string must be valid JSON or YAML; see initPodServiceAccount
 	PodServiceAccountDefinition              string            `name:"pod_service_account_definition" default:""`
 	PodServiceAccountRoleBindingDefinition   string            `name:"pod_service_account_role_binding_definition" default:""`

ui/manifests/deployment.yaml

@@ -77,7 +77,7 @@ spec:
                     "17",
                     "16",
                     "15",
-                    "14",
+                    "14"
                   ]
                 }
             # Exemple of settings to make snapshot view working in the ui when using AWS