Subscriptions

DDN Storage

DDN WOS

Object Storage

[DDNWOS]

More Image(s)


DDN WOS is Object Storage designed for the creation of almost limitless Exascale storage pools across multiple sites with bridge options into Public Cloud.


Availability: In stock

For details on how to purchase the DDN WOS, please click the button below to send us your details and brief requirements. We can then quote you accordingly.

Details

WOS Object Storage

DDN’s WOS enables organizations to build highly reliable, infinitely scalable, cost-efficient storage pools for all their unstructured data needs. Available as software or delivered as a density optimized appliance, WOS is a comprehensive and purpose-built object storage solution.

True Object Storage

WOS is enabled through DDN’s underlying NoFS (no underlying file system) architecture, which minimizes disk operations with as little as a single-disk-operation for reads, and two for writes. (This sharply contrasts with the 8-10 I/O operations that POSIX file systems require, resulting in additional performance and network overhead). Further, the infinitely variable data buckets or “sector” sizes used in WOS carefully balance performance and platter utilization, while keeping system overhead very low.

  • No Linux file I/ Os, no fragmentation.
  • Fully contiguous object read and write operations for maximum disk efficiency.

DDN WOS Key Advantages:

  • Proven at hundreds of billions of objects.
  • Delivers 20% better disk efficiency and 1.25x faster performance thanks to a no file system (NoFS®) architecture.
  • Offers the most flexible data protection models in order to tune availability, reliability and performance to the needs of the application.
  • Gives faster access to data based on built in latency mapping.
  • Starts small (1 4U system) and can scale 1 node at a time.
  • Offers unmatched metadata customization and search.
  • Provides End2End data management with a single federated namespace across high performance file storage and high capacity object storage.
  • Latency-Aware Access Manager

    In distributed environments with replicated data, WOS minimizes the access latency for end users. When a user requests an object, WOS automatically retrieves the object from the geographic node with the lowest latency.

    Meta Data Search

    WOS avoids scalability bottlenecks by storing metadata in key-value stores, rather than in scale-limiting metadata databases. A highly parallelized backend metadata search allows users to query one or more indexed fields of user-specified metadata across petabytes of objects. Applications can assign their own metadata via object storage API, WOS now also supports simple search of WOS user metadata.

    Self-Healing Architecture

    ObjectAssure, a unique form of erasure coding, has self-healing capabilities that reduce the management effort. In case of a failed disk, ObjectAssure only reconstructs the actual data that was lost, as opposed to the entire disk. In the event of an object read error, WOS automatically recreates the object from a replica or parity to fulfil the request and then replaces the object to restore compliance with the specified data protection policy. These automatic features dramatically increase data availability and reduce operator intervention. No hard tie between physical disks and data:

    • Failed drives are recovered through dispersed data placement.
    • Rebuilds happen at read, not write, speed.
    • Rebuild data, not disks.

    Flexibility

    WOS provides full flexibility to build the right storage infrastructure for any mix of applications. Customers can tune their infrastructure to meet the requirements for their data and application needs.

  • Choose data replication, erasure coding or both.
  • Protect data with smart policies for performance and/or disaster recovery on a per object basis.
  • Higher Performance

    Storage performance is measured in throughput, IOPS and latency.WOS provides the highest performance results for all three dimensions:

  • Fewer IOPS needed for each read or write (thanks to NoFS)
  • Lower latency thanks to unique latency mapping.
  • Multiple clusters can also be combined for even higher performance.
  • Part No. DDNWOS
    End of Life? No
    Width 610
    Height 1900
    Depth 1190
    Weight [Kg] 66.70
    Rack Units 4U
    Compatible CPU(s) x86 Processors
    Drive Bays Up to 72 U.2 NVMe SSDs
    Capacity 14 TB - 1 PB+
    LAN Socket(s) Ethernet (TCP and RDMA) Infiniband
    LAN Controller(s) 2-20 Active-Active Controllers
    Serial Ports 1-40 @ 40/100GBE Ports
    Storage Controller BLOCK (NVMe-oF) and FILE (NFS) Protocols
    RAID Options RAID-6, Snapshots Thin Provisioning

    Others Products of Interest

      Please login to x.com to view...