Skip to main content
Cloud / Google Cloud / Products / Local SSD - High-Performance Temporary Storage

Local SSD - High-Performance Temporary Storage

Local SSD on Google Cloud provides locally attached SSD storage for Compute Engine with very high performance.

Storage
Pricing Model Billed per GiB per month, prorated by the second
Availability Global with EU regions
Data Sovereignty EU regions available
Reliability SLA as published by the provider SLA

Local SSD on Google Cloud provides locally attached SSD storage for Compute Engine with very high performance.

What is Local SSD?

Local SSD is SSD storage physically attached to the host server for Google Compute Engine VMs. It offers very high storage performance with low latency, but is temporary and not persistent. Maximum capacity per VM depends on the machine type and can reach several dozen TiB on specialized machine types such as Z3 bare metal.

The service is available as SCSI or NVMe variants. On newer machine types such as C4, C4A, C4D, G4, H4D, and Z3, the Titanium SSD generation provides higher IOPS, higher throughput, and lower latency. Local SSD is suitable for temporary high-performance workloads such as caching, scratch storage, or database buffers.

Core Features

  • SCSI and NVMe interface, depending on machine type
  • Titanium SSD generation with higher performance on current machine families
  • Scaling IOPS and throughput with an increasing number of attached disks
  • Encryption at rest
  • Per-second billing for attached disks

Typical Use Cases

High-Performance Caching

Redis, Memcached, or Varnish caches benefit from Local SSD’s high IOPS and low latency. Data can be reloaded from the primary source if lost.

Big Data Processing (Scratch Space)

Hadoop, Spark, and similar frameworks use Local SSD for temporary shuffle data. High throughput accelerates distributed processing jobs; the data is no longer needed after job completion.

Database Buffers and Temp Tablespaces

Temporary tablespaces, redo logs, or journals benefit from low latency. Combining Persistent Disk for permanent data with Local SSD for temporary operations is common practice.

Media Rendering and Transcoding

Video rendering, image processing, and training workloads with high I/O demand benefit from local storage, which reduces network latency when reading large files. Results are saved to Cloud Storage after processing.

Benefits

  • Very high IOPS and low latency for performance-critical workloads
  • Scalable through multiple attached disks per VM
  • Titanium SSD generation on current machine types for additional performance
  • Predictable, per-second billing

Integration with innFactory

As a certified Google Cloud Partner, innFactory supports Local SSD implementations: performance optimization, data redundancy strategies, hybrid storage architectures, and disaster recovery planning.

Available Tiers & Options

SCSI

Strengths
  • High IOPS
  • Low latency
  • Cost-effective
Considerations
  • Temporary (not persistent)
  • Tied to VM lifecycle

Typical Use Cases

High IOPS workloads
Low latency applications
Temporary data processing
Caching layers

Technical Specifications

API Block device interface
Integration Native Compute Engine integration
Max size Up to several TiB per VM depending on machine type (e.g., up to 72 TiB on Z3 bare metal)
Security Encryption at rest

Frequently Asked Questions

What is Local SSD?

Local SSD is SSD storage physically attached to the host machine of a Compute Engine VM. It offers very high IOPS and very low latency, but is temporary and can be lost on VM stop, termination, or host maintenance.

What is the difference between SCSI and NVMe Local SSD?

NVMe Local SSDs offer higher throughput and lower latency through direct access, especially on newer machine types with the Titanium SSD generation. SCSI Local SSDs are sufficient for many standard workloads. Maximum capacity and disk count depend on the chosen machine type.

Is Local SSD persistent?

No, Local SSD is temporary storage. Data survives OS reboots and live migration but is lost on VM stop, termination, or preemption. For persistent data, use Persistent Disk or Filestore.

When should I use Local SSD instead of Persistent Disk?

Local SSD is suitable for temporary data with the highest performance requirements, such as caches, temporary processing, scratch space, or database buffers. Persistent Disk is the right choice for permanent storage with snapshots and replication.

How do I protect data on Local SSD?

Recommended practices include application-level replication across multiple VMs, regular backups to Cloud Storage or Persistent Disk, and planning for potential data loss on VM restart. Local SSD should never be the sole data source for critical data.

What does Local SSD cost?

Local SSD is billed per GiB per month, prorated by the second regardless of actual usage. Current prices are available in the official Google Cloud pricing list, as they can vary by region and machine type.

Note: All product information on this page has been compiled with care, but is provided without guarantee and may be outdated or incomplete. Cloud services evolve rapidly — features, pricing, SLAs, and availability change frequently. Authoritative and up-to-date information can only be found on the official product page of Google Cloud (official documentation). This page does not represent an offer by Google Cloud.

Google Cloud Partner

innFactory is a certified Google Cloud Partner. We provide expert consulting, implementation, and managed services.

Google Cloud Partner

Comparable Products from Other Clouds

As a multi-cloud partner, we help you choose the right platform for your specific requirements.

Ready to start with Local SSD - High-Performance Temporary Storage?

Our certified Google Cloud experts help you with architecture, integration, and optimization.

Schedule Consultation