Skip to content

feat(supervisor): project-based scheduling affinity for image cache locality #2995

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
myftija merged 2 commits into from
Feb 4, 2026
Merged

feat(supervisor): project-based scheduling affinity for image cache locality #2995

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
306cbc8
feat(supervisor): project-based scheduling affinity for image cache l…
myftija Feb 4, 2026
9c5be34
Add empty string guard for KUBERNETES_PROJECT_AFFINITY_TOPOLOGY_KEY
myftija Feb 4, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions apps/supervisor/src/env.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,6 +112,11 @@ const Env = z.object({
KUBERNETES_SCHEDULER_NAME: z.string().optional(), // Custom scheduler name for pods
KUBERNETES_LARGE_MACHINE_POOL_LABEL: z.string().optional(), // if set, large-* presets affinity for machinepool=<value>

// Project affinity settings - pods from the same project prefer the same node
KUBERNETES_PROJECT_AFFINITY_ENABLED: BoolEnv.default(false),
KUBERNETES_PROJECT_AFFINITY_WEIGHT: z.coerce.number().int().min(1).max(100).default(50),
KUBERNETES_PROJECT_AFFINITY_TOPOLOGY_KEY: z.string().trim().min(1).default("kubernetes.io/hostname"),

// Placement tags settings
PLACEMENT_TAGS_ENABLED: BoolEnv.default(false),
PLACEMENT_TAGS_PREFIX: z.string().default("node.cluster.x-k8s.io"),
Expand Down
88 changes: 62 additions & 26 deletions apps/supervisor/src/workloadManager/kubernetes.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,7 +120,7 @@ export class KubernetesWorkloadManager implements WorkloadManager {
},
spec: {
...this.addPlacementTags(this.#defaultPodSpec, opts.placementTags),
affinity: this.#getNodeAffinity(opts.machine),
affinity: this.#getAffinity(opts.machine, opts.projectId),
terminationGracePeriodSeconds: 60 * 60,
containers: [
{
Expand Down Expand Up @@ -390,50 +390,86 @@ export class KubernetesWorkloadManager implements WorkloadManager {
return preset.name.startsWith("large-");
}

#getNodeAffinity(preset: MachinePreset): k8s.V1Affinity | undefined {
#getAffinity(preset: MachinePreset, projectId: string): k8s.V1Affinity | undefined {
const nodeAffinity = this.#getNodeAffinityRules(preset);
const podAffinity = this.#getProjectPodAffinity(projectId);

if (!nodeAffinity && !podAffinity) {
return undefined;
}

return {
...(nodeAffinity && { nodeAffinity }),
...(podAffinity && { podAffinity }),
};
}

#getNodeAffinityRules(preset: MachinePreset): k8s.V1NodeAffinity | undefined {
if (!env.KUBERNETES_LARGE_MACHINE_POOL_LABEL) {
return undefined;
}

if (this.#isLargeMachine(preset)) {
// soft preference for the large-machine pool, falls back to standard if unavailable
return {
nodeAffinity: {
preferredDuringSchedulingIgnoredDuringExecution: [
{
weight: 100,
preference: {
matchExpressions: [
{
key: "node.cluster.x-k8s.io/machinepool",
operator: "In",
values: [env.KUBERNETES_LARGE_MACHINE_POOL_LABEL],
},
],
},
preferredDuringSchedulingIgnoredDuringExecution: [
{
weight: 100,
preference: {
matchExpressions: [
{
key: "node.cluster.x-k8s.io/machinepool",
operator: "In",
values: [env.KUBERNETES_LARGE_MACHINE_POOL_LABEL],
},
],
},
],
},
},
],
};
}

// not schedulable in the large-machine pool
return {
nodeAffinity: {
requiredDuringSchedulingIgnoredDuringExecution: {
nodeSelectorTerms: [
{
requiredDuringSchedulingIgnoredDuringExecution: {
nodeSelectorTerms: [
{
matchExpressions: [
{
key: "node.cluster.x-k8s.io/machinepool",
operator: "NotIn",
values: [env.KUBERNETES_LARGE_MACHINE_POOL_LABEL],
},
],
},
],
},
};
}

#getProjectPodAffinity(projectId: string): k8s.V1PodAffinity | undefined {
if (!env.KUBERNETES_PROJECT_AFFINITY_ENABLED) {
return undefined;
}

return {
preferredDuringSchedulingIgnoredDuringExecution: [
{
weight: env.KUBERNETES_PROJECT_AFFINITY_WEIGHT,
podAffinityTerm: {
labelSelector: {
matchExpressions: [
{
key: "node.cluster.x-k8s.io/machinepool",
operator: "NotIn",
values: [env.KUBERNETES_LARGE_MACHINE_POOL_LABEL],
key: "project",
operator: "In",
values: [projectId],
},
],
},
],
topologyKey: env.KUBERNETES_PROJECT_AFFINITY_TOPOLOGY_KEY,
},
},
},
],
};
}
}
Loading