IBM Spectrum

IBM Spectrum Scale, based on IBM General Parallel File System (GPFS™) , is a proven, scalable, high-performance file management system that is being used extensively across multiple industries worldwide. IBM Spectrum Scale provides simplified data management and integrated information lifecycle tools capable of managing petabytes of data and billions of files, in order to address the growing cost of managing ever growing amounts of data.

Some of the key benefits of IBM Spectrum Scale:

  • Modern scale out architecture
  • A global namespace that can spans datacenters and the globe
  • Access file data directly or using NFS, SMB, Object and Hadoop
  • Virtually limitless performance and capacity scaling
  • Automated data placement and data migration
  • Leverage less expensive commodity storage
  • Integrated with IBM Spectrum Archive and IBM Spectrum Protect
  • A long history of proven reliability across multiple industries

What IBM Spectrum Scale can do for your business

Enterprises and organizations are creating, analyzing and keeping more data than ever before. Those that can deliver insights faster while managing rapid infrastructure growth are the leaders in their industry. In delivering those insights, an organization’s underlying storage must support new-era big data and artificial intelligence workloads along with traditional applications while ensuring security, reliability and high performance. IBM Spectrum Scale™ meets these challenges as a high-performance solution for managing data at scale with the distinctive ability to perform archive and analytics in place.

Key features of IBM Spectrum Scale

  • Provides extreme scalability
  • Reduces storage costs
  • Improves security and management efficiency
  • Global file sharing with active file management
  • Transforms data economics
  • Manage and gain insights from massive amounts of data
  • Available on Amazon Web Services

Feature spotlights

Reduces storage costs

You can cut costs up to 90% with intelligent archiving and automatic policy-based storage
tiering from flash through disk to tape.

Improves security and management efficiency

Colin Morey, system architect, explains how Hartree Centre uses the management
efficiency capabilities of IBM Spectrum Scale to help connect scientists and industry.

Transforms data economics

IBM Spectrum Scale transforms data economics for traditional and next-generation
applications with great speed, agility and efficiency.

Manage and gain insights from massive amounts of data

IBM Spectrum Discover is modern metadata management software that provides data
insight for petabyte-scale unstructured storage. It connects to IBM Spectrum Scale or IBM
Cloud Object Storage to rapidly ingest, consolidate and index metadata for billions of files
and objects, enabling data scientists, storage administrators, and data stewards to
efficiently manage, classify and gain insights from massive amounts of unstructured data.

Technical details

Software requirements

No software requirements for IBM Spectrum Scale

Hardware requirements

Hardware supported: x86 architecture: Intel EM64T processors or AMD Opteron, minimum 1 GB system memory IBM POWER® architecture: AIX v6.1 or v7.1, Linux on POWER3 (minimum), minimum 1 GB system memory; z Systems (Linux only)

IBM AIX®; Linux: Red Hat, SUSE Linux Enterprise Server; Microsoft Windows Server 2012, Microsoft Windows 7; IBM z Systems™

Technical specifications

Operating systems supported: IBM AIX®; Linux: Red Hat, SUSE Linux Enterprise Server; Microsoft Windows Server 2012, Microsoft Windows 7; IBM z Systems™

Protocols: POSIX, GPFS, NFS v4.0, SMB v3.0; Big data and analytics: Hadoop MapReduce; Cloud: OpenStack Cinder (block), OpenStack Swift (object), S3 (object)

Cloud object storage: IBM Cloud Storage System (Cleversafe), Amazon S3, IBM Cloud Native Object, OpenStack Swift and Amazon S3 compatible providers

  • Maximum number of files/file system: 264 (9 quintillion) files per file system
  • Maximum file system size: 8 Exabytes (EB)
  • Minimum/maximum number of nodes: 1 - 16,384