diff --git a/api/v1alpha1/mcpserver_types.go b/api/v1alpha1/mcpserver_types.go index 95570e1..cefa64e 100644 --- a/api/v1alpha1/mcpserver_types.go +++ b/api/v1alpha1/mcpserver_types.go @@ -341,6 +341,15 @@ type MCPServerDeployment struct { // +optional Affinity *corev1.Affinity `json:"affinity,omitempty"` + // TopologySpreadConstraints defines the topology spread constraints for the pod. + // Use this to control how pods are spread across topology domains + // such as zones, regions, or nodes for high availability. + // +optional + // +patchStrategy=replace + // +listType=map + // +listMapKey=name + TopologySpreadConstraints []corev1.TopologySpreadConstraint `json:"topologySpreadConstraints,omitempty"` + // NodeSelector defines the node selector for the pod. // Use this to constrain pods to nodes with specific labels. // +optional diff --git a/api/v1alpha1/zz_generated.deepcopy.go b/api/v1alpha1/zz_generated.deepcopy.go index b305b9d..a110d75 100644 --- a/api/v1alpha1/zz_generated.deepcopy.go +++ b/api/v1alpha1/zz_generated.deepcopy.go @@ -22,7 +22,7 @@ package v1alpha1 import ( corev1 "k8s.io/api/core/v1" - v1 "k8s.io/apimachinery/pkg/apis/meta/v1" + "k8s.io/apimachinery/pkg/apis/meta/v1" runtime "k8s.io/apimachinery/pkg/runtime" ) @@ -210,6 +210,13 @@ func (in *MCPServerDeployment) DeepCopyInto(out *MCPServerDeployment) { *out = new(corev1.Affinity) (*in).DeepCopyInto(*out) } + if in.TopologySpreadConstraints != nil { + in, out := &in.TopologySpreadConstraints, &out.TopologySpreadConstraints + *out = make([]corev1.TopologySpreadConstraint, len(*in)) + for i := range *in { + (*in)[i].DeepCopyInto(&(*out)[i]) + } + } if in.NodeSelector != nil { in, out := &in.NodeSelector, &out.NodeSelector *out = make(map[string]string, len(*in)) diff --git a/config/crd/bases/kagent.dev_mcpservers.yaml b/config/crd/bases/kagent.dev_mcpservers.yaml index de1da0a..9d4ac55 100644 --- a/config/crd/bases/kagent.dev_mcpservers.yaml +++ b/config/crd/bases/kagent.dev_mcpservers.yaml @@ -3383,6 +3383,188 @@ spec: type: string type: object type: array + topologySpreadConstraints: + description: |- + TopologySpreadConstraints defines the topology spread constraints for the pod. + Use this to control how pods are spread across topology domains + such as zones, regions, or nodes for high availability. + items: + description: TopologySpreadConstraint specifies how to spread + matching pods among the given topology. + properties: + labelSelector: + description: |- + LabelSelector is used to find matching pods. + Pods that match this label selector are counted to determine the number of pods + in their corresponding topology domain. + properties: + matchExpressions: + description: matchExpressions is a list of label selector + requirements. The requirements are ANDed. + items: + description: |- + A label selector requirement is a selector that contains values, a key, and an operator that + relates the key and values. + properties: + key: + description: key is the label key that the selector + applies to. + type: string + operator: + description: |- + operator represents a key's relationship to a set of values. + Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: |- + values is an array of string values. If the operator is In or NotIn, + the values array must be non-empty. If the operator is Exists or DoesNotExist, + the values array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + x-kubernetes-list-type: atomic + required: + - key + - operator + type: object + type: array + x-kubernetes-list-type: atomic + matchLabels: + additionalProperties: + type: string + description: |- + matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, whose key field is "key", the + operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + matchLabelKeys: + description: |- + MatchLabelKeys is a set of pod label keys to select the pods over which + spreading will be calculated. The keys are used to lookup values from the + incoming pod labels, those key-value labels are ANDed with labelSelector + to select the group of existing pods over which spreading will be calculated + for the incoming pod. The same key is forbidden to exist in both MatchLabelKeys and LabelSelector. + MatchLabelKeys cannot be set when LabelSelector isn't set. + Keys that don't exist in the incoming pod labels will + be ignored. A null or empty list means only match against labelSelector. + + This is a beta field and requires the MatchLabelKeysInPodTopologySpread feature gate to be enabled (enabled by default). + items: + type: string + type: array + x-kubernetes-list-type: atomic + maxSkew: + description: |- + MaxSkew describes the degree to which pods may be unevenly distributed. + When `whenUnsatisfiable=DoNotSchedule`, it is the maximum permitted difference + between the number of matching pods in the target topology and the global minimum. + The global minimum is the minimum number of matching pods in an eligible domain + or zero if the number of eligible domains is less than MinDomains. + For example, in a 3-zone cluster, MaxSkew is set to 1, and pods with the same + labelSelector spread as 2/2/1: + In this case, the global minimum is 1. + | zone1 | zone2 | zone3 | + | P P | P P | P | + - if MaxSkew is 1, incoming pod can only be scheduled to zone3 to become 2/2/2; + scheduling it onto zone1(zone2) would make the ActualSkew(3-1) on zone1(zone2) + violate MaxSkew(1). + - if MaxSkew is 2, incoming pod can be scheduled onto any zone. + When `whenUnsatisfiable=ScheduleAnyway`, it is used to give higher precedence + to topologies that satisfy it. + It's a required field. Default value is 1 and 0 is not allowed. + format: int32 + type: integer + minDomains: + description: |- + MinDomains indicates a minimum number of eligible domains. + When the number of eligible domains with matching topology keys is less than minDomains, + Pod Topology Spread treats "global minimum" as 0, and then the calculation of Skew is performed. + And when the number of eligible domains with matching topology keys equals or greater than minDomains, + this value has no effect on scheduling. + As a result, when the number of eligible domains is less than minDomains, + scheduler won't schedule more than maxSkew Pods to those domains. + If value is nil, the constraint behaves as if MinDomains is equal to 1. + Valid values are integers greater than 0. + When value is not nil, WhenUnsatisfiable must be DoNotSchedule. + + For example, in a 3-zone cluster, MaxSkew is set to 2, MinDomains is set to 5 and pods with the same + labelSelector spread as 2/2/2: + | zone1 | zone2 | zone3 | + | P P | P P | P P | + The number of domains is less than 5(MinDomains), so "global minimum" is treated as 0. + In this situation, new pod with the same labelSelector cannot be scheduled, + because computed skew will be 3(3 - 0) if new Pod is scheduled to any of the three zones, + it will violate MaxSkew. + format: int32 + type: integer + nodeAffinityPolicy: + description: |- + NodeAffinityPolicy indicates how we will treat Pod's nodeAffinity/nodeSelector + when calculating pod topology spread skew. Options are: + - Honor: only nodes matching nodeAffinity/nodeSelector are included in the calculations. + - Ignore: nodeAffinity/nodeSelector are ignored. All nodes are included in the calculations. + + If this value is nil, the behavior is equivalent to the Honor policy. + This is a beta-level feature default enabled by the NodeInclusionPolicyInPodTopologySpread feature flag. + type: string + nodeTaintsPolicy: + description: |- + NodeTaintsPolicy indicates how we will treat node taints when calculating + pod topology spread skew. Options are: + - Honor: nodes without taints, along with tainted nodes for which the incoming pod + has a toleration, are included. + - Ignore: node taints are ignored. All nodes are included. + + If this value is nil, the behavior is equivalent to the Ignore policy. + This is a beta-level feature default enabled by the NodeInclusionPolicyInPodTopologySpread feature flag. + type: string + topologyKey: + description: |- + TopologyKey is the key of node labels. Nodes that have a label with this key + and identical values are considered to be in the same topology. + We consider each as a "bucket", and try to put balanced number + of pods into each bucket. + We define a domain as a particular instance of a topology. + Also, we define an eligible domain as a domain whose nodes meet the requirements of + nodeAffinityPolicy and nodeTaintsPolicy. + e.g. If TopologyKey is "kubernetes.io/hostname", each Node is a domain of that topology. + And, if TopologyKey is "topology.kubernetes.io/zone", each zone is a domain of that topology. + It's a required field. + type: string + whenUnsatisfiable: + description: |- + WhenUnsatisfiable indicates how to deal with a pod if it doesn't satisfy + the spread constraint. + - DoNotSchedule (default) tells the scheduler not to schedule it. + - ScheduleAnyway tells the scheduler to schedule the pod in any location, + but giving higher precedence to topologies that would help reduce the + skew. + A constraint is considered "Unsatisfiable" for an incoming pod + if and only if every possible node assignment for that pod would violate + "MaxSkew" on some topology. + For example, in a 3-zone cluster, MaxSkew is set to 1, and pods with the same + labelSelector spread as 3/1/1: + | zone1 | zone2 | zone3 | + | P P P | P | P | + If WhenUnsatisfiable is set to DoNotSchedule, incoming pod can only be scheduled + to zone2(zone3) to become 3/2/1(3/1/2) as ActualSkew(2-1) on zone2(zone3) satisfies + MaxSkew(1). In other words, the cluster can still be imbalanced, but scheduler + won't make it *more* imbalanced. + It's a required field. + type: string + required: + - maxSkew + - topologyKey + - whenUnsatisfiable + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map volumeMounts: description: |- VolumeMounts defines the list of volume mounts for the MCP server container. diff --git a/helm/kmcp-crds/templates/mcpserver-crd.yaml b/helm/kmcp-crds/templates/mcpserver-crd.yaml index de1da0a..9d4ac55 100644 --- a/helm/kmcp-crds/templates/mcpserver-crd.yaml +++ b/helm/kmcp-crds/templates/mcpserver-crd.yaml @@ -3383,6 +3383,188 @@ spec: type: string type: object type: array + topologySpreadConstraints: + description: |- + TopologySpreadConstraints defines the topology spread constraints for the pod. + Use this to control how pods are spread across topology domains + such as zones, regions, or nodes for high availability. + items: + description: TopologySpreadConstraint specifies how to spread + matching pods among the given topology. + properties: + labelSelector: + description: |- + LabelSelector is used to find matching pods. + Pods that match this label selector are counted to determine the number of pods + in their corresponding topology domain. + properties: + matchExpressions: + description: matchExpressions is a list of label selector + requirements. The requirements are ANDed. + items: + description: |- + A label selector requirement is a selector that contains values, a key, and an operator that + relates the key and values. + properties: + key: + description: key is the label key that the selector + applies to. + type: string + operator: + description: |- + operator represents a key's relationship to a set of values. + Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: |- + values is an array of string values. If the operator is In or NotIn, + the values array must be non-empty. If the operator is Exists or DoesNotExist, + the values array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + x-kubernetes-list-type: atomic + required: + - key + - operator + type: object + type: array + x-kubernetes-list-type: atomic + matchLabels: + additionalProperties: + type: string + description: |- + matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, whose key field is "key", the + operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + matchLabelKeys: + description: |- + MatchLabelKeys is a set of pod label keys to select the pods over which + spreading will be calculated. The keys are used to lookup values from the + incoming pod labels, those key-value labels are ANDed with labelSelector + to select the group of existing pods over which spreading will be calculated + for the incoming pod. The same key is forbidden to exist in both MatchLabelKeys and LabelSelector. + MatchLabelKeys cannot be set when LabelSelector isn't set. + Keys that don't exist in the incoming pod labels will + be ignored. A null or empty list means only match against labelSelector. + + This is a beta field and requires the MatchLabelKeysInPodTopologySpread feature gate to be enabled (enabled by default). + items: + type: string + type: array + x-kubernetes-list-type: atomic + maxSkew: + description: |- + MaxSkew describes the degree to which pods may be unevenly distributed. + When `whenUnsatisfiable=DoNotSchedule`, it is the maximum permitted difference + between the number of matching pods in the target topology and the global minimum. + The global minimum is the minimum number of matching pods in an eligible domain + or zero if the number of eligible domains is less than MinDomains. + For example, in a 3-zone cluster, MaxSkew is set to 1, and pods with the same + labelSelector spread as 2/2/1: + In this case, the global minimum is 1. + | zone1 | zone2 | zone3 | + | P P | P P | P | + - if MaxSkew is 1, incoming pod can only be scheduled to zone3 to become 2/2/2; + scheduling it onto zone1(zone2) would make the ActualSkew(3-1) on zone1(zone2) + violate MaxSkew(1). + - if MaxSkew is 2, incoming pod can be scheduled onto any zone. + When `whenUnsatisfiable=ScheduleAnyway`, it is used to give higher precedence + to topologies that satisfy it. + It's a required field. Default value is 1 and 0 is not allowed. + format: int32 + type: integer + minDomains: + description: |- + MinDomains indicates a minimum number of eligible domains. + When the number of eligible domains with matching topology keys is less than minDomains, + Pod Topology Spread treats "global minimum" as 0, and then the calculation of Skew is performed. + And when the number of eligible domains with matching topology keys equals or greater than minDomains, + this value has no effect on scheduling. + As a result, when the number of eligible domains is less than minDomains, + scheduler won't schedule more than maxSkew Pods to those domains. + If value is nil, the constraint behaves as if MinDomains is equal to 1. + Valid values are integers greater than 0. + When value is not nil, WhenUnsatisfiable must be DoNotSchedule. + + For example, in a 3-zone cluster, MaxSkew is set to 2, MinDomains is set to 5 and pods with the same + labelSelector spread as 2/2/2: + | zone1 | zone2 | zone3 | + | P P | P P | P P | + The number of domains is less than 5(MinDomains), so "global minimum" is treated as 0. + In this situation, new pod with the same labelSelector cannot be scheduled, + because computed skew will be 3(3 - 0) if new Pod is scheduled to any of the three zones, + it will violate MaxSkew. + format: int32 + type: integer + nodeAffinityPolicy: + description: |- + NodeAffinityPolicy indicates how we will treat Pod's nodeAffinity/nodeSelector + when calculating pod topology spread skew. Options are: + - Honor: only nodes matching nodeAffinity/nodeSelector are included in the calculations. + - Ignore: nodeAffinity/nodeSelector are ignored. All nodes are included in the calculations. + + If this value is nil, the behavior is equivalent to the Honor policy. + This is a beta-level feature default enabled by the NodeInclusionPolicyInPodTopologySpread feature flag. + type: string + nodeTaintsPolicy: + description: |- + NodeTaintsPolicy indicates how we will treat node taints when calculating + pod topology spread skew. Options are: + - Honor: nodes without taints, along with tainted nodes for which the incoming pod + has a toleration, are included. + - Ignore: node taints are ignored. All nodes are included. + + If this value is nil, the behavior is equivalent to the Ignore policy. + This is a beta-level feature default enabled by the NodeInclusionPolicyInPodTopologySpread feature flag. + type: string + topologyKey: + description: |- + TopologyKey is the key of node labels. Nodes that have a label with this key + and identical values are considered to be in the same topology. + We consider each as a "bucket", and try to put balanced number + of pods into each bucket. + We define a domain as a particular instance of a topology. + Also, we define an eligible domain as a domain whose nodes meet the requirements of + nodeAffinityPolicy and nodeTaintsPolicy. + e.g. If TopologyKey is "kubernetes.io/hostname", each Node is a domain of that topology. + And, if TopologyKey is "topology.kubernetes.io/zone", each zone is a domain of that topology. + It's a required field. + type: string + whenUnsatisfiable: + description: |- + WhenUnsatisfiable indicates how to deal with a pod if it doesn't satisfy + the spread constraint. + - DoNotSchedule (default) tells the scheduler not to schedule it. + - ScheduleAnyway tells the scheduler to schedule the pod in any location, + but giving higher precedence to topologies that would help reduce the + skew. + A constraint is considered "Unsatisfiable" for an incoming pod + if and only if every possible node assignment for that pod would violate + "MaxSkew" on some topology. + For example, in a 3-zone cluster, MaxSkew is set to 1, and pods with the same + labelSelector spread as 3/1/1: + | zone1 | zone2 | zone3 | + | P P P | P | P | + If WhenUnsatisfiable is set to DoNotSchedule, incoming pod can only be scheduled + to zone2(zone3) to become 3/2/1(3/1/2) as ActualSkew(2-1) on zone2(zone3) satisfies + MaxSkew(1). In other words, the cluster can still be imbalanced, but scheduler + won't make it *more* imbalanced. + It's a required field. + type: string + required: + - maxSkew + - topologyKey + - whenUnsatisfiable + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map volumeMounts: description: |- VolumeMounts defines the list of volume mounts for the MCP server container. diff --git a/pkg/controller/transportadapter/transportadapter_translator.go b/pkg/controller/transportadapter/transportadapter_translator.go index c8e463f..c53971a 100644 --- a/pkg/controller/transportadapter/transportadapter_translator.go +++ b/pkg/controller/transportadapter/transportadapter_translator.go @@ -178,6 +178,7 @@ func (t *transportAdapterTranslator) translateTransportAdapterDeployment( Tolerations: server.Spec.Deployment.Tolerations, Affinity: server.Spec.Deployment.Affinity, NodeSelector: server.Spec.Deployment.NodeSelector, + TopologySpreadConstraints: server.Spec.Deployment.TopologySpreadConstraints, InitContainers: []corev1.Container{{ Name: "copy-binary", Image: transportAdapterContainerImage, @@ -251,6 +252,7 @@ func (t *transportAdapterTranslator) translateTransportAdapterDeployment( Tolerations: server.Spec.Deployment.Tolerations, Affinity: server.Spec.Deployment.Affinity, NodeSelector: server.Spec.Deployment.NodeSelector, + TopologySpreadConstraints: server.Spec.Deployment.TopologySpreadConstraints, Containers: append([]corev1.Container{ { Name: "mcp-server",