liveBook · Manning

IOPS

As explained in MongoDB 8.0 in Action, Third Edition

IOPS is the number of input and output operations that a storage system can perform per second.

IOPS measures how many input and output operations a storage system can perform each second. In Atlas, provisioned IOPS customize a cluster’s maximum IOPS rate, improving consistency and reducing p90 latency. section 10.2.4

Atlas storage changes make IOPS an operational setting as well as a performance metric:

  • AWS-backed M30+ clusters support provisioned IOPS for a more consistent rate and faster response times. section 10.2.4
  • Storage and IOPS changes follow different provider-specific rules; decreases can require new volumes, data synchronization, node replacement, or initial syncs. section 10.2.4
  • Multicloud deployments use the lowest common denominator across providers to preserve consistency. section 10.2.4

How MongoDB 8.0 in Action, Third Edition covers it

How deep it goes
Explains provisioned-rate benefits and provider-specific change behavior, but does not develop an independent performance model.
Examples
Uses AWS-backed M30+ clusters, general-purpose SSD volumes, NVMe storage, and provider-specific storage changes.
What it assumes
Assumes familiarity with Atlas clusters, storage capacity, cloud providers, and p90 latency.
What you can do after
Operate/configure Atlas storage by selecting provisioned IOPS and anticipating provider-specific capacity-change consequences.
How it connects
Connects storage capacity, p90 latency, provisioned IOPS, cloud providers, and multicloud deployments.
Cover of MongoDB 8.0 in Action, Third Edition
liveBookmanning.com
Read MongoDB 8.0 in Action, Third Edition on liveBook Get the book at manning.com

Also explained in

Compare how 2 books explain IOPS →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of MongoDB 8.0 in Action, Third Edition. The section links point to the parts of the book it draws on.