Sign up for our newsletter and get the latest big data news and analysis.
Daily
Weekly

IBM Launches Storage for Data Management across Hybrid Clouds

IBM has announced innovations across its storage product line designed to improve management of data across complex hybrid cloud environments with the goal of improving data availability and resilience. The company announced plans to launch container-native software defined storage (SDS), IBM Spectrum Fusion, in the second half of 2021 designed to combine IBM’s parallel file system with data protection software  in the data center, at the edge and across hybrid cloud environments.

IBM also introduced updates to its IBM Elastic Storage System (ESS) line of high-performance solutions designed for scalability  and easier deployment. The company said the model ESS 5000 delivers 10 percent more capacity and the ESS 3200 offers double the read performance of its predecessor.

In its announcement, IBM said that as hybrid cloud adoption grows, so does the need to manage the edge of the network. Often geographically dispersed and disconnected from the data center, edge computing can strand vast amounts of data that could be otherwise brought to bear on analytics and AI. Like the digital universe, the edge continues to expand, creating ever more disassociated data sources and silos.  The company cited a report from IDC[3] stating that the number of new operational processes deployed on edge infrastructure will grow from less than 20 percent today to over 90 percent in 2024[4] as digital engineering accelerates IT/OT convergence. And By 2022, IDC estimates that 80 percent of organizations that shift to a hybrid business by design will boost spend on AI-enabled and secure edge infrastructure by 4x[5] to deliver business agility and insights in near real time.

“It’s clear that to build, deploy and manage applications requires advanced capabilities that help provide rapid availability to data across the entire enterprise – from the edge to the data center to the cloud,” said Denis Kennelly, General Manager, IBM Storage Systems. “It’s not as easy as it sounds, but it starts with building a foundational data layer, a containerized information architecture and the right storage infrastructure.”

Guardant Health, one of the leading precision oncology companies, is dedicated to helping conquer cancer globally through use of its proprietary blood tests, vast data sets, and advanced analytics. The company is committed to helping patients across the cancer care continuum live longer, healthier lives. The company’s data and high-performance computing platforms turn massive amounts of genomic data into actionable insights for oncologists, researchers, and the biopharmaceutical industry, with unparalleled speed and throughput. Several years ago it turned to IBM to help it build a data foundation for its platform knowing that it needed to scale its data infrastructure to serve the tens of millions of patients around the world, and across the cancer care continuum.

“We manage large scale compute clusters demanding high data throughput to a large number of compute nodes,” said Kumud Kalia, CIO, Guardant Health. “IBM Spectrum Scale’s parallel filesystem delivers high performance, while the ESS systems provide the data throughput our genomic pipelines require. I look forward to continued collaboration with IBM to further innovate on this platform.”

The first version of IBM Spectrum Fusion is planned to come in the form of a container-native hyperconverged infrastructure (HCI) system, according to IBM. It will integrate compute, storage and networking into a single solution. It is being designed to come equipped with Red Hat OpenShift to enable organizations to support environments for both virtual machines and containers and provide software defined storage for cloud, edge and containerized data centers, the company said.

In early 2022, IBM plans to release an SDS-only version of IBM Spectrum Fusion.

With the IBM Spectrum Fusion solutions, organizations will be able to manage a single copy of data, the company said, avoiding duplication of data when moving application workloads. In addition, data compliance activities can be improved by a single copy of data, while security exposure from the presence of multiple copies is reduced, the company said.

Spectrum Fusion also will integrate with IBM Cloud Satellite to help enable businesses to fully manage cloud services at the edge, data center or in the public cloud with a single management pane. It also being designed to integrate with Red Hat Advanced Cluster Manager (ACM) for managing multiple Red Hat OpenShift clusters.

The new IBM ESS models include:

  • Global Data Boost: The IBM ESS 3200, a new 2U storage solution that is designed to provide data throughput of 80 GB/second per node – a 100 percent read performance improvement over its predecessor[6], the ESS 3000. Also adding to its performance, the 3200 supports up to 8 InfiniBand HDR-200 or Ethernet-100 ports. The system can also provide up to 367TB of storage capacity per 2U node.
  • Packing on the Petabytes: In addition, the IBM ESS 5000 model has been updated to support 10 percent more density than previously available for a total storage capacity of 15.2PB. In addition, all ESS systems are now equipped with streamlined containerized deployment capabilities automated with the latest version of Red Hat Ansible.

Both the ESS 3200 and ESS 5000 feature containerized system software and support for Red Hat OpenShift and Kubernetes Container Storage Interface (CSI), CSI snapshots and clones, Red Hat Ansible, Windows, Linux and bare metal environments. The systems also come with IBM Spectrum Scale built-in.

In addition, the 3200 and 5000 also work with IBM Cloud Pak for Data, the company’s containerized platform of data and AI services, for integration with IBM Watson Knowledge Catalog (WKC) and Db2. WKC is a cloud-based enterprise metadata repository that activates information for AI, machine learning and deep learning. Users rely on it to access, curate, categorize and share data, knowledge assets and their relationships. IBM Db2 for Cloud Pak for Data is an AI-infused data management system built on Red Hat OpenShift.

To bring together edge computing, core data center, private and public cloud environments, IBM said the ESS 3200 and 5000 are integrated with IBM Cloud Satellite.

[3] IDC FutureScape: Worldwide Future of Operations 2021 Predictions, October 2020.

[4] Ibid.

[5] Ibid.

[6] The ESS 3200 performance was measured using the IBM Large File Sequential Read Bandwidth test, which is based on the industry standard benchmark, IOR.

Leave a Comment

*

Resource Links: