Skip to content

Served models on tainted GPU nodes can't get Longhorn storage #124

Description

@dcmcand

Found while testing #117 live on an AWS Nebari cluster.

When GPU nodes carry a taint (e.g. nvidia.com/gpu) and Longhorn's components do not tolerate it, longhorn-manager is not scheduled on the GPU nodes, so they never register as Longhorn nodes and Longhorn cannot attach PVCs there:

FailedAttachVolume: ... unable to attach volume <pvc> to <gpu-node>:
node.longhorn.io "<gpu-node>" not found

The pack defaults model storage to the longhorn StorageClass (defaults.storage.storageClassName), so a served LLMModel scheduled onto a tainted GPU node gets stuck in Init with its model-storage PVC unattached, and never serves.

Workaround (per model): set spec.model.storage.storageClassName to a class that attaches on the GPU node, e.g. gp2/EBS (WaitForFirstConsumer, provisions in the node's AZ).

Suggested fix: document this for GPU node groups, and/or default served-model storage to a node-local class when the model requests a GPU. Not addressed by code yet.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    Priority

    None yet

    Start date

    None yet

    Target date

    None yet

    Size

    None yet

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions