Configuring Power Management

Owned by Rumena Zlatkova (Deactivated)
Last updated: Dec 12, 2023 by Bala Harish A(AC)
3 min read

Swarm includes an adaptive power conservation feature that supplements Swarm's naturally green characteristics. This power-saving mode, also referred to as Darkive™, spins down disks and reduces CPU utilization after a configurable period of inactivity.

In the Swarm UI, the options appear under the Power section of the Cluster Settings page:

Tip

The configuration options for power management apply to the entire cluster.

How Power Management Works

The power-saving mode causes a node with no incoming SCSP requests (from clients or other Swarm nodes) in the last configurable power.sleepAfter seconds to change to an Idle status and pause its health processor. There is usually a delay between the node Idle status and its volumes Idle status because in-process replications are performed between nodes even after they are idle, to guarantee full data protection. After all queued activity is completed, the disks eventually spin down (if supported by the disk manufacturer) and display as Idle if no further activity causes disk I/O.

When it appears in the Swarm UI or Console, Idle has different meanings for a node and volume:

  • Idle Node: A node with no SCSP activity for a specified length of time. In an idle state, a node's health processor pauses, so an idle node is more likely to have idle volumes.

  • Idle Volume: A volume with no I/O activity for at least six minutes.

The cluster automatically wakes one or more nodes to carry out requests when needed and eventually revives all nodes if required. If there is no intervening activity after the configured power.wakeAfter period, the cluster wakes all nodes to perform data, disk, and replication integrity checks.

Power Management Settings

Adjust these settings to best suit your Swarm implementation:

power.savingMode

Enables Power Saving Mode, which allows the system to sleep or power cap. Set to False to disable, which is called Full Performance Mode.

A cluster with long periods of inactivity on nights and weekends can achieve significant power savings using this feature. Because only inactive nodes are affected, maximum available throughput is not affected, although additional latency is incurred on the first access to a node.

Best Practice

Use Full Performance Mode (power.savingMode = False) for these situations:

  • The cluster is in constant use (24x7).

  • Uninterrupted feed restarts are critical for your operations.

  • The cluster is used for direct replication (DR).

power.sleepAfter

In seconds, 60 or greater; defaults to 2 hours. In Power Saving mode, how long a node is inactive before it becomes idle.

This option determines how long a period of inactivity should occur with no incoming SCSP requests before Swarm pauses the node's health processor and displays it as Idle in the Swarm UI or Console. If you select Full Performance Mode, a node does not display as Idle. Setting the value to a small number allows nodes to become idle after a reasonable period of inactivity (two hours by default).

Important

Avoid setting this value to a long period, which prevents Swarm nodes from becoming idle and taking advantage of power savings.

power.wakeAfter

In seconds; defaults to 8 hours. In Power Saving mode, how long a node is idle before it becomes active again.

This option determines how long a node remains idle before Swarm wakes up an idle node to allow the health processor to validate disk content integrity and replicas. Setting the number to a small number reduces power savings, although the volumes and nodes return to an Idle state if additional client activity is not received.



© DataCore Software Corporation. · https://www.datacore.com · All rights reserved.