Merge pull request #2653 from malayparida2000/full_settings

Expose ceph full threshold settings in StorageCluster CR

api/v1/storagecluster_types.go

@@ -198,6 +198,21 @@ type ManageCephCluster struct {
 	// default DOWN/OUT interval) when it is draining. This is only relevant when  `managePodBudgets` is `true` in cephCluster CR.
 	// The default value is `30` minutes.
 	OsdMaintenanceTimeout time.Duration `json:"osdMaintenanceTimeout,omitempty"`
+	// FullRatio is the ratio at which the cluster is considered full and ceph will stop accepting writes. Default is 0.95.
+	// +kubebuilder:validation:Minimum=0.0
+	// +kubebuilder:validation:Maximum=1.0
+	// +nullable
+	FullRatio *float64 `json:"fullRatio,omitempty"`
+	// NearFullRatio is the ratio at which the cluster is considered nearly full and will raise a ceph health warning. Default is 0.85.
+	// +kubebuilder:validation:Minimum=0.0
+	// +kubebuilder:validation:Maximum=1.0
+	// +nullable
+	NearFullRatio *float64 `json:"nearFullRatio,omitempty"`
+	// BackfillFullRatio is the ratio at which the cluster is too full for backfill. Backfill will be disabled if above this threshold. Default is 0.90.
+	// +kubebuilder:validation:Minimum=0.0
+	// +kubebuilder:validation:Maximum=1.0
+	// +nullable
+	BackfillFullRatio *float64 `json:"backfillFullRatio,omitempty"`
 }
 
 // ManageCephConfig defines how to reconcile the Ceph configuration

config/crd/bases/ocs.openshift.io_storageclusters.yaml

@@ -725,10 +725,26 @@ spec:
                     description: ManageCephCluster defines how to reconcile the Ceph
                       cluster definition
                     properties:
+                      backfillFullRatio:
+                        description: BackfillFullRatio is the ratio at which the cluster
+                          is too full for backfill. Backfill will be disabled if above
+                          this threshold. Default is 0.90.
+                        maximum: 1
+                        minimum: 0
+                        nullable: true
+                        type: number
                       continueUpgradeAfterChecksEvenIfNotHealthy:
                         description: Whether or not continue if PGs are not clean
                           during an upgrade
                         type: boolean
+                      fullRatio:
+                        description: FullRatio is the ratio at which the cluster is
+                          considered full and ceph will stop accepting writes. Default
+                          is 0.95.
+                        maximum: 1
+                        minimum: 0
+                        nullable: true
+                        type: number
                       mgrCount:
                         enum:
                         - 1
@@ -739,6 +755,14 @@ spec:
                         - 3
                         - 5
                         type: integer
+                      nearFullRatio:
+                        description: NearFullRatio is the ratio at which the cluster
+                          is considered nearly full and will raise a ceph health warning.
+                          Default is 0.85.
+                        maximum: 1
+                        minimum: 0
+                        nullable: true
+                        type: number
                       osdMaintenanceTimeout:
                         description: A duration in minutes that determines how long
                           an entire failureDomain like `region/zone/host` will be

controllers/storagecluster/cephcluster.go

@@ -464,6 +464,9 @@ func newCephCluster(sc *ocsv1.StorageCluster, cephImage string, kmsConfigMap *co
 				StorageClassDeviceSets:       newStorageClassDeviceSets(sc),
 				Store:                        osdStore,
 				FlappingRestartIntervalHours: 24,
+				FullRatio:                    sc.Spec.ManagedResources.CephCluster.FullRatio,
+				NearFullRatio:                sc.Spec.ManagedResources.CephCluster.NearFullRatio,
+				BackfillFullRatio:            sc.Spec.ManagedResources.CephCluster.BackfillFullRatio,
 			},
 			Placement: rookCephv1.PlacementSpec{
 				"all":     getPlacement(sc, "all"),

deploy/csv-templates/crds/ocs/ocs.openshift.io_storageclusters.yaml

@@ -725,10 +725,26 @@ spec:
                     description: ManageCephCluster defines how to reconcile the Ceph
                       cluster definition
                     properties:
+                      backfillFullRatio:
+                        description: BackfillFullRatio is the ratio at which the cluster
+                          is too full for backfill. Backfill will be disabled if above
+                          this threshold. Default is 0.90.
+                        maximum: 1
+                        minimum: 0
+                        nullable: true
+                        type: number
                       continueUpgradeAfterChecksEvenIfNotHealthy:
                         description: Whether or not continue if PGs are not clean
                           during an upgrade
                         type: boolean
+                      fullRatio:
+                        description: FullRatio is the ratio at which the cluster is
+                          considered full and ceph will stop accepting writes. Default
+                          is 0.95.
+                        maximum: 1
+                        minimum: 0
+                        nullable: true
+                        type: number
                       mgrCount:
                         enum:
                         - 1
@@ -739,6 +755,14 @@ spec:
                         - 3
                         - 5
                         type: integer
+                      nearFullRatio:
+                        description: NearFullRatio is the ratio at which the cluster
+                          is considered nearly full and will raise a ceph health warning.
+                          Default is 0.85.
+                        maximum: 1
+                        minimum: 0
+                        nullable: true
+                        type: number
                       osdMaintenanceTimeout:
                         description: A duration in minutes that determines how long
                           an entire failureDomain like `region/zone/host` will be

deploy/ocs-operator/manifests/ocs-operator.clusterserviceversion.yaml

@@ -585,7 +585,7 @@ spec:
                 - name: OCS_METRICS_EXPORTER_IMAGE
                   value: quay.io/ocs-dev/ocs-metrics-exporter:latest
                 - name: ROOK_CEPH_IMAGE
-                  value: quay.io/ocs-dev/rook-ceph:vmaster-75180f4f3
+                  value: quay.io/ocs-dev/rook-ceph:vmaster-19a200ac8
                 - name: CEPH_IMAGE
                   value: quay.io/ceph/ceph:v18.2.0
                 - name: NOOBAA_CORE_IMAGE
@@ -742,7 +742,7 @@ spec:
   provider:
     name: Red Hat
   relatedImages:
-  - image: quay.io/ocs-dev/rook-ceph:vmaster-75180f4f3
+  - image: quay.io/ocs-dev/rook-ceph:vmaster-19a200ac8
     name: rook-container
   - image: quay.io/ceph/ceph:v18.2.0
     name: ceph-container

deploy/ocs-operator/manifests/storagecluster.crd.yaml

@@ -724,10 +724,26 @@ spec:
                     description: ManageCephCluster defines how to reconcile the Ceph
                       cluster definition
                     properties:
+                      backfillFullRatio:
+                        description: BackfillFullRatio is the ratio at which the cluster
+                          is too full for backfill. Backfill will be disabled if above
+                          this threshold. Default is 0.90.
+                        maximum: 1
+                        minimum: 0
+                        nullable: true
+                        type: number
                       continueUpgradeAfterChecksEvenIfNotHealthy:
                         description: Whether or not continue if PGs are not clean
                           during an upgrade
                         type: boolean
+                      fullRatio:
+                        description: FullRatio is the ratio at which the cluster is
+                          considered full and ceph will stop accepting writes. Default
+                          is 0.95.
+                        maximum: 1
+                        minimum: 0
+                        nullable: true
+                        type: number
                       mgrCount:
                         enum:
                         - 1
@@ -738,6 +754,14 @@ spec:
                         - 3
                         - 5
                         type: integer
+                      nearFullRatio:
+                        description: NearFullRatio is the ratio at which the cluster
+                          is considered nearly full and will raise a ceph health warning.
+                          Default is 0.85.
+                        maximum: 1
+                        minimum: 0
+                        nullable: true
+                        type: number
                       osdMaintenanceTimeout:
                         description: A duration in minutes that determines how long
                           an entire failureDomain like `region/zone/host` will be

go.mod

@@ -31,19 +31,19 @@ require (
 	github.com/prometheus-operator/prometheus-operator/pkg/client v0.72.0
 	github.com/red-hat-storage/ocs-client-operator v0.0.0-20240325165741-300e2b620f51
 	github.com/red-hat-storage/ocs-operator/api/v4 v4.0.0-20240327160100-bbe9d9d49462
-	github.com/rook/rook/pkg/apis v0.0.0-20240513003450-39f88521f0fd
+	github.com/rook/rook/pkg/apis v0.0.0-20240607162148-886c94854899
 	github.com/stretchr/testify v1.9.0
 	go.uber.org/multierr v1.11.0
-	golang.org/x/net v0.23.0
+	golang.org/x/net v0.25.0
 	google.golang.org/grpc v1.62.1
 	google.golang.org/protobuf v1.33.0
 	gopkg.in/ini.v1 v1.67.0
 	gopkg.in/yaml.v3 v3.0.1
 	gotest.tools/v3 v3.5.1
-	k8s.io/api v0.29.3
+	k8s.io/api v0.29.5
 	k8s.io/apiextensions-apiserver v0.29.2
-	k8s.io/apimachinery v0.29.3
-	k8s.io/client-go v0.29.3
+	k8s.io/apimachinery v0.29.5
+	k8s.io/client-go v0.29.5
 	k8s.io/klog/v2 v2.120.1
 	k8s.io/utils v0.0.0-20240310230437-4693a0247e57
 	sigs.k8s.io/controller-runtime v0.17.2
@@ -85,13 +85,13 @@ require (
 	github.com/hashicorp/errwrap v1.1.0 // indirect
 	github.com/hashicorp/go-cleanhttp v0.5.2 // indirect
 	github.com/hashicorp/go-multierror v1.1.1 // indirect
-	github.com/hashicorp/go-retryablehttp v0.7.5 // indirect
+	github.com/hashicorp/go-retryablehttp v0.7.6 // indirect
 	github.com/hashicorp/go-rootcerts v1.0.2 // indirect
 	github.com/hashicorp/go-secure-stdlib/parseutil v0.1.8 // indirect
 	github.com/hashicorp/go-secure-stdlib/strutil v0.1.2 // indirect
 	github.com/hashicorp/go-sockaddr v1.0.6 // indirect
 	github.com/hashicorp/hcl v1.0.1-vault-5 // indirect
-	github.com/hashicorp/vault/api v1.13.0 // indirect
+	github.com/hashicorp/vault/api v1.14.0 // indirect
 	github.com/hashicorp/vault/api/auth/approle v0.6.0 // indirect
 	github.com/hashicorp/vault/api/auth/kubernetes v0.6.0 // indirect
 	github.com/josharian/intern v1.0.0 // indirect
@@ -118,12 +118,12 @@ require (
 	github.com/tidwall/pretty v1.2.0 // indirect
 	go.mongodb.org/mongo-driver v1.9.0 // indirect
 	go.uber.org/zap v1.26.0 // indirect
-	golang.org/x/crypto v0.21.0 // indirect
+	golang.org/x/crypto v0.23.0 // indirect
 	golang.org/x/exp v0.0.0-20231127185646-65229373498e // indirect
 	golang.org/x/oauth2 v0.18.0 // indirect
-	golang.org/x/sys v0.18.0 // indirect
-	golang.org/x/term v0.18.0 // indirect
-	golang.org/x/text v0.14.0 // indirect
+	golang.org/x/sys v0.20.0 // indirect
+	golang.org/x/term v0.20.0 // indirect
+	golang.org/x/text v0.15.0 // indirect
 	golang.org/x/time v0.5.0 // indirect
 	golang.org/x/tools v0.18.0 // indirect
 	gomodules.xyz/jsonpatch/v2 v2.4.0 // indirect