|
The IBM General Parallel File System™ (GPFS™) is a high-performance scalable file management solution that provides fast, reliable access to a common set of file data from a single computer to hundreds of systems. GPFS integrates into your environment by bringing together mixed server and storage components to provide a common view to enterprise file data. GPFS provides online storage management, scalable access and integrated information lifecycle tools capable of managing petabytes of data and billions of files.
GPFS allows multiple systems and applications to share common pools of storage. This allows the virtualization of the file storage space and the ability to transparently administer the infrastructure without disrupting applications. GPFS supports multi-vendor storage and server hardware, enabling striping, replication and snapshots across heterogeneous systems.
Reduce management overhead by using GPFS to share a common set of files concurrently across multiple systems. Even a subset of GPFS systems can serve the data over NFS while others concurrently run applications that require high performance direct SAN access to the files. GPFS includes tools for highly scalable NFS. For a scalable NAS solution that supports multiple protocols including CIFS see the Scale out File Services (SoFS) solution.
GPFS is an essential component to implementing a high throughput grid environment. High-availability features including data replication and automatic failure handling provide a solid base on which to build an analytics grid or digital media management system. GPFS Network Shared Disk technology allows extreme scalability by enabling network attached nodes to be tightly integrated into the solution. For an overview of GPFS availability features see An introduction to the IBM General Parallel File System (GPFS) 3.1.
Storage pools and the highly scalable policy engine can introduce structure to your unstructured data. GPFS can manage billions of files using the integrated SQL based policies for file placement and migration. The scalable policy engine can be run on one system or concurrently on all systems depending on processing needs. For more information read Implementing a Scalable Information Lifecycle Solution using IBM GPFS.
| 
