initiate_roll
Initiate a rolling restart of nodes in an Ocean cluster by draining and replacing them in configurable batches to maintain service availability during updates.
Instructions
DESTRUCTIVE: Initiate a rolling restart of nodes in an Ocean cluster. This will drain and replace nodes in batches. Requires confirm=true.
Args: cluster_id: The Ocean cluster ID (e.g. o-abc12345) confirm: Must be true to execute. Safety guard against accidental rolls. batch_size_percentage: Percentage of nodes to roll per batch (default: 20) batch_min_healthy_percentage: Min healthy nodes per batch (default: 50) respect_pdb: Respect PodDisruptionBudgets (default: true) launch_spec_ids: Comma-separated VNG IDs to roll (e.g. ols-abc,ols-def). Empty = all. instance_ids: Comma-separated instance IDs to roll. Empty = all in scope. account_id: Optional account ID. Defaults to SPOTINST_ACCOUNT_ID env var. cloud: Cloud provider: aws or azure (default: aws)
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cluster_id | Yes | ||
| confirm | No | ||
| batch_size_percentage | No | ||
| batch_min_healthy_percentage | No | ||
| respect_pdb | No | ||
| launch_spec_ids | No | ||
| instance_ids | No | ||
| account_id | No | ||
| cloud | No | aws |