Whether to support the session persistence function at the pod level

[xigua88-66]

What would you like to be added?

We are using k8s for cluster management of multiple GPU servers (multiple GPU cards), and the same AI model will be deployed on each GPU machine and provide services. However, a complete use of some AI services requires multiple http requests to complete. We hope that these HTTP requests all run on the same pod, because the data needs to be loaded into the GPU, otherwise other GPU servers or received requests will lack data and the call will fail.

In addition to using ClientIP for session persistence in sessionAffinity, does it support custom session persistence functions, such as defining a group of HTTP requests that need to be forwarded to the same pod?

Why is this needed?

Customize http request distribution

[k8s-ci-robot]

There are no sig labels on this issue. Please add an appropriate label by using one of the following commands:

• /sig <group-name>
• /wg <group-name>
• /committee <group-name>

Please see the group list for a listing of the SIGs, working groups, and committees available.

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository.

[k8s-ci-robot]

This issue is currently awaiting triage.

If a SIG or subproject determines this is a relevant issue, they will accept it by applying the triage/accepted label and provide further guidance.

The triage/accepted label can be added by org members by writing /triage accepted in a comment.

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository.

[LuBingtan]

It seems that Istio ConsistentHashLB is just what you are looking for.

[sftim]

Relevant to kubernetes-sigs/gateway-api#1619

[k8s-triage-robot]

The Kubernetes project currently lacks enough contributors to adequately respond to all issues.

This bot triages un-triaged issues according to the following rules:

• After 90d of inactivity, lifecycle/stale is applied
• After 30d of inactivity since lifecycle/stale was applied, lifecycle/rotten is applied
• After 30d of inactivity since lifecycle/rotten was applied, the issue is closed

You can:

• Mark this issue as fresh with /remove-lifecycle stale
• Close this issue with /close
• Offer to help out with Issue Triage

Please send feedback to sig-contributor-experience at kubernetes/community.

/lifecycle stale

[k8s-triage-robot]

The Kubernetes project currently lacks enough active contributors to adequately respond to all issues.

This bot triages un-triaged issues according to the following rules:

• After 90d of inactivity, lifecycle/stale is applied
• After 30d of inactivity since lifecycle/stale was applied, lifecycle/rotten is applied
• After 30d of inactivity since lifecycle/rotten was applied, the issue is closed

You can:

• Mark this issue as fresh with /remove-lifecycle rotten
• Close this issue with /close
• Offer to help out with Issue Triage

Please send feedback to sig-contributor-experience at kubernetes/community.

/lifecycle rotten

[neolit123]

/close
/kind support

please reopen if needed.

[k8s-ci-robot]

@neolit123: Closing this issue.

In response to this:

/close
/kind support

please reopen if needed.

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository.