Reserve more than 1 vCPU for IRQ handling

[zimnx]

On bigger machines, we need more power to handle IRQ. ScyllaDB recommendation for 16 core machine is to reserve 2 vcpu for IRQ, and the rest for DB. Currenly, on 16 core machine, scheulder will schedule 15 Guaranteed QoS ScyllaClusters having 1vcpu because there's nothing preventing from it. This will lead to just 1 vCPU handling the IRQ and the rest stuff running on the Node.

We should have a way to reserve a number of vCPU specificly for IRQ handling and other Pods running per each NUMA node on the Node.

[scylla-operator-bot[bot]]

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

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

• After 30d 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

/lifecycle stale

[tnozicka]

/remove-lifecycle stale /triage accepted

[scylla-operator-bot[bot]]

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

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

• After 30d 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

/lifecycle rotten

[tnozicka]

/remove-lifecycle stale /triage accepted