EMC Elastic Cloud Storage

EMC Elastic Cloud Storage (ECS), formerly Project Nile,^[1] is a software-defined Object storage platform marketed by EMC Corporation. ECS was designed to adhere to several tenets of object storage, including scalability, data resiliency and to take advantage of existing or new commodity server hardware in order to manage costs. At an architectural level, EMC ECS offers Software-defined storage (SDS).

This flexibility not only simplifies the deployment of ECS, but it also allows ECS to provide a single pool of data that can spread data across a variety of underlying infrastructure components, including commodity or ECS appliances, and even EMC and third-party storage arrays. In addition to the flexibility offered by the software-based architecture, ECS enables multi-head access, allowing different protocols, such as object and HDFS, to access the same data concurrently.^[1]

The ECS Appliance is available in multiple form factors that can be deployed and expanded incrementally, starting at 320 Terabytes and scaling to 3.8 Petabytes in a single rack configuration. It is deployable in clusters for additional petabyte and exabyte scalability. In addition, ECS is available as a software-only solution that can be deployed on qualified, 3rd-party customer provided racking.^[2]

Applications

EMC Elastic Cloud Storage has a number of applications, including the Internet of things^[3] and financial services, where it was determined by Cohasset Associates Inc. to meet “the relevant storage requirements of SEC Rule 17a-4(f) and CFTC Rule 1.31(b)-(c)” when “Compliance is enabled for a Namespace and when properly configured and utilized to store and retain records in non-erasable and non-rewriteable format.”^[4] Its use of object storage and flat namespace, according to the Edison Group, “allows for multiple types of data to be stored side by side. Regardless of the data, it is all viewed as object, their globally unique IDs, and metadata.”^[3] This approach allows multiple data types from multiple sources to be stored alongside one another, including:

• Large data sets: Financial, pharmaceutical, geospatial, biotech, and legal
• Public data sets: Weather, government
• Security, imagery, and social media: Images, videos, blogs
• Revenue chain data: Sensors, devices, Internet of Things^[5]

Technology and Architecture

According to The Enterprise Strategy Group, “EMC’s ECS solution is, at an architectural level, software-defined storage (SDS). While the term SDS is used by multiple offerings and providers and can have multiple definitions, for ECS, an SDS architecture means that the solution can be procured as a purely software solution and deployed on the commodity server hardware infrastructure of the organization’s choosing, or as an appliance with the software preinstalled on commodity hardware from EMC.”^[2] The ECS platform includes the following software layers and services:

• ECS Portal Services include interfaces for provisioning, managing, and monitoring storage resources. The interfaces include a built-in browser-based graphical user interface called the ECS Portal, a RESTful API to customize individual ECS Portals and a command line interface.
• ECS Storage Services are provided by the unstructured storage engine (USE), which ensures data availability and protection against data corruption, hardware failures, and data center disasters. It enables global namespace management across geographically dispersed data centers and geo-replication. The USE enables object, file and HDFS. The object service provides the ability to store, access, and manipulate unstructured data. It is compatible with existing Amazon S3, OpenStack Swift APIs, EMC CAS, and EMC Atmos APIs. HDFS enables the use of the portal storage infrastructure as a Big Data repository for Hadoop analytic applications.
• The ECS Provisioning Service manages the provisioning of storage resources and user access. It handles user management, authorization and authentication for all provisioning requests, resource management and multi-tenancy support.
• The ECS Fabric Service is a distributed cluster manager that is responsible for cluster, node and disk health, as well as for software management.
• The ECS Infrastructure Service layer provides the Linux OS running on the commodity nodes and it implements network interfaces and other hardware-related tools. It uses SUSE Linux Enterprise Server 12 as the base operating system for the turnkey appliance, or other qualified Linux operating systems for a DIY commodity hardware configuration.^[6]

Industry Recognition

• ECS was recognized as the leader in Object storage for 2014 by IDC.^[7] (note: EMC’s bubble size is reflective of only ECS)

References

1. "EMC Debuts Elastic Cloud Storage Appliance, Updates Software-Defined Storage Platform". TheWHIR.
2. "EMC Elastic Cloud Storage Offers Resilient Scalability for the New Generation of Workloads" (PDF). Enterprise Strategy Group.
3. "Bridging the Infrastructure Gap for the Internet of Things with Object Storage" (PDF). Edison Group.
4. "SEC 17a-4(f) & CFTC 1.31(b)-(c) Compliance Assessment: EMC Elastic Cloud Storage (ECS)" (PDF). Cohasset Associates Inc.
5. "EMC Elastic Cloud Storage Offers Resilient Scalability for the New Generation of Workloads" (PDF). Enterprise Strategy Group.
6. "EMC Elastic Cloud Storage (ECS) Overview and Architecture" (PDF). EMC Corporation.
7. "IDC MarketScape: Worldwide Object-Based Storage 2014 Vendor Assessment" (PDF). IDC.