Yandex Cloud
Search
Contact UsGet started
  • Pricing
  • Customer Stories
  • Documentation
  • Blog
  • All Services
  • System Status
    • Featured
    • Infrastructure & Network
    • Data Platform
    • Containers
    • Developer tools
    • Serverless
    • Security
    • Monitoring & Resources
    • AI Studio
    • Business tools
  • All Solutions
    • By industry
    • By use case
    • Economics and Pricing
    • Security
    • Technical Support
    • Start testing with double trial credits
    • Cloud credits to scale your IT product
    • Gateway to Russia
    • Cloud for Startups
    • Education and Science
    • Yandex Cloud Partner program
  • Pricing
  • Customer Stories
  • Documentation
  • Blog
© 2025 Direct Cursus Technology L.L.C.
Yandex Data Processing
  • Getting started
    • Service resource interdependencies
    • Runtime environment
    • Yandex Data Processing component interfaces and ports
    • Yandex Data Processing jobs
    • Spark jobs
    • Autoscaling
    • Decommissioning of subclusters and hosts
    • Yandex Data Processing network
    • Maintenance
    • Quotas and limits
    • Yandex Data Processing storage
    • Component settings
    • Apache Iceberg™ in Yandex Data Processing
    • Delta Lake in Yandex Data Processing
    • Yandex Data Processing logs
    • Initialization scripts
  • Access management
  • Pricing policy
  • Terraform reference
  • Monitoring metrics
  • Audit Trails events
  • Public materials
  • FAQ
  1. Concepts
  2. Yandex Data Processing storage

Storage in Yandex Data Processing

Written by
Yandex Cloud
Updated at July 9, 2025

Yandex Data Processing enables you to use network storage drives to store subclusters. Network drives are based on network blocks, which are virtual disks in the Yandex Cloud infrastructure.

When creating a cluster, you can choose between the following storage types:

  • Network HDD storage (network-hdd): Most cost-effective option for clusters that do not require high read/write performance.

  • Network SSD storage (network-ssd): Balanced solution. Such disks are slower than non-replicated SSDs, but, unlike non-replicated disks, they ensure data integrity in case Yandex Cloud hardware fails.

  • Non-replicated SSD storage (network-ssd-nonreplicated): Network SSDs with enhanced performance achieved by eliminating redundancy.

    The storage size can only be increased in 93 GB increments.

    For more information about this disk type, see the Yandex Compute Cloud documentation.

Note

Up to 5% of disk space is reserved for system use, so the disks may have less available space than indicated when creating a cluster.

For more information about sizes and performance of different disk types, see the Yandex Compute Cloud documentation.

Specifics of non-replicated SSD storageSpecifics of non-replicated SSD storage

Non-replicated SSD storage does not provide fault tolerance; this means, if a disk fails, the data is permanently lost.

Was the article helpful?

Previous
Quotas and limits
Next
Component settings
© 2025 Direct Cursus Technology L.L.C.