Systems Hardware

Data Sheet

IBM Spectrum Scale

Performance and simplicity for the
hybrid cloud
Highlights

• Consolidate storage across

the hybrid cloud
• Achieve new operational
efficiency and cost
effectiveness
• Help lower data retention
cost up to 90% with policy-
driven automation
• Improve application
performance with scale-out
and flash-based
acceleration
• Enable collaboration and
IBM Spectrum Scale has a simple message
efficient sharing of
resources among global
teams
• Transparently tier/achive to Enterprises and organizations are creating, analyzing and
multi-cloud or local tape or keeping more data than ever before. Those that can deliver
low-cost media insights faster while managing rapid infrastructure growth are
• Built in enterprise security the leaders in their industry. To deliver those insights, an
for compliance and organization’s underlying storage must support both new-
business requirements era, big-data applications and traditional applications with
high performance, reliability and security. To handle massive
• Containerized for modern
applicaitons
unstructured data growth, storage must scale seamlessly
while matching data value to the capabilities and costs of
• Deploy in public cloud to
different storage tiers and types. IBM Spectrum Scale meets
create a true hybrid cloud
these challenges and more. It is a high-performance parallel
data access
file system for managing data at scale with the distinctive
ability to perform archive and analytics in place.
Systems Hardware
Data Sheet

Part of the IBM Spectrum Storage family of solutions, IBM Spectrum Scale is an enterprise-
grade parallel file system that provides superior resiliency, scalability and control. Based on IBM
General Parallel File System (GPFS), IBM Spectrum Scale delivers scalable capacity and
performance to handle demanding data analytics, content repositories and technical computing
workloads. Storage administrators can combine flash, disk, cloud, and tape storage into a
unified system with higher performance and lower cost than traditional approaches. With
thousands of customers and nearly 20 years of demanding production deployments, IBM
Spectrum Scale is a file system that can adapt to both application performance and capacity
needs across the enterprise. By including IBM Spectrum Scale in their software-defined
infrastructure, organizations can streamline data workflows, help improve service, reduce costs,
manage risk and deliver business results today while positioning the enterprise for future
growth.

IBM Spectrum Scale enables the unification of virtualization, analytics, file and object use cases
into a single scale-out storage solution. It can provide a single namespace for all of this data,
offering a single point of management with an intuitive graphical user interface (GUI). Using
storage policies transparent to end users, data can be compressed or tiered to tape or cloud to
help cut costs; data can also be tiered to high-performance media, including server cache, to
lower latency and improve performance. Intelligent caching of data at remote sites ensures that
data is available with local read/write performance across geographically distributed sites using
Active File Management (AFM).

Simplified data management at scale

IBM Spectrum scale is a parallel file system, where the intelligence is in the client and the client
spreads the load across all storage nodes in a cluster, even for individual files. In traditional
scale-out network-attached storage (NAS), one file can only be accessed through one node at a
time by an individual client, limiting performance and scalability. By contrast, the IBM Spectrum
Scale architecture allows it to seamlessly handle tens of thousands of clients, billions of files
and yottabytes of data.

IBM Spectrum Scale allows different applications or services to access the same data without
moving or altering it. Data can be written and retrieved as either files or objects. Rather than use
a copy and change gateway, IBM Spectrum Scale supports both protocols natively for higher
performance and simplified administration. The common storage layer enables most IBM
Spectrum Scale features, including authentication, encryption and tiering, for both object and
file storage.
Systems Hardware
Data Sheet

Simple to manage and configure

IBM Spectrum Scale includes integrated management tools and an intuitive GUI to help manage
data at scale. The system can span multiple storage environments and data centers to eliminate
data silos and “filer sprawl.” It can automatically spread data across multiple storage
devices—optimizing available storage utilization, reducing administration and delivering high
performance where needed. IBM Spectrum Scale has multiple deployment options and
configurations to incorporate current NFS filers, block storage and storage-rich servers into a
global namespace with universal access. Its file system supports interfaces for file (POSIX, NFS,
CIFS), object (S3, SWIFT) and Hadoop Distributed File System (HDFS) for in-place analytics. IBM
Spectrum Scale is the caretaker of business-critical data with the ability to replicate, encrypt,
compress, and distribute data across different hardware platforms, systems and data centers.

Global collaboration
Systems Hardware
Data Sheet

One global file system with built-in data protection

IBM Spectrum Scale enables low-latency read and write access to data from anywhere in the
world using AFM distributed routing and advanced caching technology. AFM expands the IBM
Spectrum Scale global namespace across geographical distances, providing fast read and write
performance with automated namespace management. As data is written or modified at one
location, all other locations get the same data with minimal delays. AFM leverages the inherent
scalability of IBM Spectrum Scale, providing a high-performance, location-independent solution
that masks network failures and hides wide-area latencies and outages. These game-changing
capabilities accelerate project schedules and improve productivity for globally distributed
teams.

Advanced data management

Data lifecycle management

IBM Spectrum Scale can help improve performance, lower costs, add resiliency and simplify
collaboration with algorithmic and policy-driven data movement, copying and caching. IBM
Spectrum Scale catalogs data across multiple storage pools, including the cloud. It tracks usage
profiles, storage latency and a broad range of standard and custom metadata from which data
movement policies can be constructed.

Armed with the knowledge of the data usage and the underlying storage, IBM Spectrum Scale
curates data across multiple tiers of storage, including tape and cloud. The powerful, data-
aware intelligence engine can create optimized tiered storage pools by grouping devices—flash,
Systems Hardware
Data Sheet

solid-state drive (SSD), disk or tape—based on performance, locality or cost. Migration policies
transparently move data from one storage pool to another without changing the file’s location in
the directory structure. Automated analysis of data usage patterns can help administrators pull
data back up to higher performance tiers as needed. The information lifecycle management
toolset built into IBM Spectrum Scale helps simplify data management by enabling additional
control over data placement. The toolset includes storage pooling and a high-performance,
scalable, rule-based policy engine.

IBM Spectrum Scale supports Hadoop workloads and HDFS—without requiring any changes to
applications. With IBM Spectrum Scale HDFS Transparency connector, multiple IBM Spectrum
Scale clusters or another HDFS repository can be federated into a single HDFS instance. This
reduces the need to move data, simplifying the deployment and workflow of Hadoop, Apache
Spark and related packages.

End-to-end data availability, reliability and integrity

IBM Spectrum Scale provides system scalability, very high availability and reliability with no
single point of failure in large-scale storage infrastructures. Administrators can configure the file
system so that it automatically remains available if a disk or server fails. The system is designed
to transparently fail over metadata operations and other services, which can be distributed
throughout the entire cluster. For additional reliability, IBM Spectrum Scale supports snapshots,
synchronous and asynchronous replication, and asynchronous error diagnosis while affected
input/output (I/O) operations continue. IBM Spectrum Scale offers protection of data at rest and
secure deletion with file-level encryption. It can encrypt data in flight or at rest with
independent key management that integrates with leading enterprise key management
systems. IBM Spectrum Scale can be part of the enterprise disaster-recovery plans with the
ability to quickly back up, copy and restore data as needed. With automatic fail-over and
intelligent fail-back, IBM Spectrum Scale keeps businesses and organizations up and running.

Using Transparent Cloud Tiering, public cloud or on-premises IBM Cloud Object Storage can be
added as a tier of storage. Ideal for adding active archive storage pools or taking advantage of
storage as a service, the design leaves end users unaffected by data movement to and from the
cloud. IBM Spectrum Scale manages the metadata, movement and caching to seamlessly tier to
and from any Amazon S3 or OpenStack Swift storage without the inconvenience, complexity and
performance hit of adding a separate cloud or object storage silo.

IBM Spectrum Scale Innovations

Systems Hardware
Data Sheet

Innovation within the IBM Spectrum Scale platform continues at a brisk pace. IBM Spectrum
Scale includes these new capabilities and enhancements, among many others:

A new level of storage performance and efficiency

Dramatic improvements in I/O performance

Significantly reduced inter-node software path latency to support the newest low-latency,
high-bandwidth hardware such as NVMe

Improved performance for many small and large block size workloads simultaneously from
new 4 MB default block size with variable sub-block size based on block size choice

Improved metadata operation performance to a single directory from multiple nodes

Simpler, more powerful system administration

Faster and simpler out-of-the-box experience with tuning of an additional 20+

communication protocol and buffer management parameters now handled automatically,
aiding setup for optimal performance

Enhanced GUI features for many capabilities, including performance, capacity, network
monitoring, AFM (multi-cluster management), Transparent Cloud Tiering, and enhanced
maintenance and support, including interaction with IBM remote support

Security enhancements for management of sensitive data

New file audit logging capability to track user accesses to filesystem and events supported
across all nodes and all protocols

Parsable data stored in secure retention-protected fileset

A third-generation Representational State Transfer (REST) application programming interface

(API) that allows modern, highly automated, cloud-ready management and monitoring, along
with remote operation of IBM Spectrum Scale clusters

Expanded Transparent Cloud Tiering support with better granularity of data and support for
multiple cloud accounts and multiple containers

Better backup/restore via new support of snapshots, better performance via improved load
balancing, and better production vs. recovery prioritization

Faster implementation and deployment in IBM Elastic Storage Server environments with
enhanced Call Home configuration and network pre-checking
Systems Hardware
Data Sheet

IBM Spectrum Scale in Public Cloud

IBM Spectrum Scale in AWS

IBM Spectrum Scale is available in AWS marketplace and includes a supported reference
architectures. IBM Spectrum Scale on AWS is configured in a high-performance tier in AWS for
AI and other high-performance applications and can be configured with the ESS 5000 and ESS
3000 or any IBM Spectrum Scale configuration.

IBM Spectrum Scale for Kuberneties Containers

Systems Hardware
Data Sheet

Containerized for simplicity

IBM Spectrum Scale has containerized the storage access inside a Kuberneties container.
Storage deployed inside containers, alongside applications running in containers, is an
important innovation that benefits both developers and administrators. By containerizing
storage services and managing them under a single management plane such as Kubernetes,
administrators have fewer housekeeping tasks to deal with, allowing them to focus on more
value-added tasks. Developers benefit by being able to provision application storage
themselves that’s both highly elastic and developer-friendly. With IBM Spectrum Scale
container native storage access there are no limits of localized disks and performance is not
effected by the application server but is optimized by external storage resources. IBM Spectrum
Scale provides most of the benefits of container native storage without the limits of using only
local disk and application server performance.

More than a product - a hybrid cloud data modernization strategy

Systems Hardware
Data Sheet

IBM Spectrum Scale

IBM Spectrum Scale has a simple message, Secure access. Anywhere. Enterprise data services.
Everywhere. Hybrid cloud. Anyone. IBM Spectrum Scale is the center of IBM Storage for Data
and AI information architecture. Its a global hybrid cloud file system with parallel access and is
the glue that creates a hybrid cloud storage solution for an AI information architecture for any
enterprise or organization.

IBM Spectrum Scale at a glance

Systems Hardware
Data Sheet

Why IBM? For more information

The message for IBM Spectrum Scale is To learn more about IBM Spectrum Scale,
simple: High performance parallel data please contact your IBM representative or
access with enterprise data services IBM Business Partner, or visit:
connecting edge to core to public cloud in a http://www.ibm.com/products/spectrum-sc
single cluster. IBM Spectrum Scale is a ale
marketing leading storage solution for AI,
Analytics, HPC and any high performance or
capacity file storage workload.
Systems Hardware
Data Sheet

© Copyright IBM Corporation 2022.

IBM, the IBM logo, and ibm.com are trademarks of

International Business Machines Corp., registered in
many jurisdictions worldwide. Other product and
service names might be trademarks of IBM or other
companies. A current list of IBM trademarks is
available on the Web at
https://www.ibm.com/legal/us/en/copytrade.shtml, Intel, Intel logo, Intel Inside, Intel Inside logo, Intel
and select third party trademarks that might be Centrino, Intel Centrino logo, Celeron, Intel Xeon,
referenced in this document is available at Intel SpeedStep, Itanium, and Pentium are
https://www.ibm.com/legal/us/en/copytrade.shtml#se trademarks or registered trademarks of Intel
ction_4. Corporation or its subsidiaries in the United States
and other countries.
This document contains information pertaining to the
following IBM products which are trademarks and/or Linux is a registered trademark of Linus Torvalds in
registered trademarks of IBM Corporation: the United States, other countries, or both.
IBM®, IBM Z®, POWER6®, Spectrum Scale™, IBM
Spectrum Storage™, IBM General Parallel File System Microsoft, Windows, Windows NT, and the Windows
(GPFS™), IBM Elastic Storage™, IBM Power logo are trademarks of Microsoft Corporation in the
Systems™, IBM LinuxONE™, IBM Spectrum Archive™ United States, other countries, or both.

All statements regarding IBM's future direction and

intent are subject to change or withdrawal without
notice, and represent goals and objectives only.