High-performance block storage for VMs with Persistent Disk and Hyperdisk for flexible performance scaling.
What is Google Cloud Block Storage?
Google Cloud Block Storage encompasses the block storage product family consisting of Persistent Disk and Hyperdisk. Both provide network-based block storage volumes for Compute Engine VMs but differ in their scaling architecture. Persistent Disk scales performance proportionally to disk size, while Hyperdisk allows IOPS, throughput, and capacity to be adjusted independently.
Hyperdisk is the latest generation of block storage in Google Cloud. With Hyperdisk Balanced, Extreme, ML, and Throughput, the product family covers all performance requirements. Hyperdisk Balanced is suited for general production workloads, Extreme for latency-sensitive databases, ML for machine learning training with high throughput, and Throughput for sequential batch processing.
Both product lines offer encryption-at-rest, incremental snapshots, and integration with Google Kubernetes Engine. Volumes can be moved between VMs and attached to multiple VMs simultaneously in read-only mode.
Core Features
- Flexible Performance: Hyperdisk enables independent scaling of IOPS, throughput, and capacity
- Snapshots: Incremental, globally available snapshots for backup and disaster recovery
- Encryption: Standard encryption-at-rest with optional Customer-Managed Keys (CMEK)
- Multi-Attach: Read-only attachment to multiple VMs for shared storage scenarios
Typical Use Cases
Database Workloads with Variable Requirements
Databases with changing load profiles benefit from Hyperdisk Balanced or Extreme. IOPS and throughput can be dynamically adjusted without stopping the VM or resizing the disk. This reduces costs and enables on-demand performance.
ML Training with High Throughput
Machine learning training requires high sequential throughput for loading large datasets. Hyperdisk ML is specifically optimized for these workloads and offers up to 1,200 MB/s throughput per volume.
Benefits
- Independent scaling of performance and capacity with Hyperdisk
- Wide selection of storage tiers for every workload type
- Seamless integration with Compute Engine and GKE
- Automatic replication and snapshots for data protection
Integration with innFactory
As a Google Cloud partner, innFactory supports you with Block Storage: storage architecture design, migration from existing block storage solutions, performance optimization, and cost management.
Typical Use Cases
Frequently Asked Questions
What is Google Cloud Block Storage?
Google Cloud Block Storage includes Persistent Disk and Hyperdisk, providing block storage volumes for Compute Engine VMs. Persistent Disk offers Standard, Balanced, Performance, and Extreme tiers, while Hyperdisk enables independently scalable IOPS and throughput values.
What is the difference between Persistent Disk and Hyperdisk?
Persistent Disk scales performance with disk size. Hyperdisk decouples performance from capacity and allows independent adjustment of IOPS, throughput, and storage. Hyperdisk is ideal for workloads with variable performance requirements.
What Hyperdisk types are available?
Hyperdisk Balanced for general workloads, Hyperdisk Extreme for highest IOPS requirements, Hyperdisk ML for ML training workloads with high throughput, and Hyperdisk Throughput for sequential workloads with high throughput.
