Bookmark and Share

Value in your organization is driven by the ability to access and analyze data regardless of object size, object count or storage amount. Advancements across various industries are making maintaining value more difficult exposing the limitations of file system based storage technologies which become brittle with size and have constraining file count limits based on the inefficiencies of splitting files into blocks. The solution is the Caringo object storage platform powered by CAStor that enables boundless storage solutions for big data.

Billions of Objects without Degradation in Performance

Caringo object storage for big data was designed with massive scale in mind and can store billions of objects of any size without degradation in performance under a single namespace. The built in HTTP interface guarantees accessibility from any application while intelligent policy driven management and automatic optimization ensure plug-and-play expansion to petabytes per location.

  • Massively scale capacity – meet any demand — Scale by simply inserting one, or more nodes into the cluster. Additional capacity is automatically available; no provisioning by an administrator. Minimize administrative overhead to increase storage up to petabytes of capacity in a single cluster.
  • Simple, adaptive, symmetric software — CAStor uses symmetric clusters to evenly distribute processing across all nodes. Performance is continuously monitored by using adaptive algorithms to identify the optimal nodes, at any point in time, for requested operations.
  • Unlimited flat address space — A single, flat 128-bit address space enables extremely efficient replication and migration. It provides massive and seamless scalability, long-term archiving and the flexibility to join or split storage infrastructures, all without changes to the application.
  • No file system limitations — Universally unique IDs stored in a flat address space eliminate the complexity of hierarchical file system architectures. There are no limits on quantity of files and no capacity limits. Achieve the performance of primary storage for content of all types, large or small.
  • Easy to increase throughput — Insert a new node into the cluster and it is automatically recognized and capacity is pooled with the overall cluster capacity without downtime or impact to applications.

The University of Utrecht is efficiently archiving raw research data using object storage.

The University of Utrecht in the Netherlands fosters innovative research that contributes to economic development and the solution of social issues such as climate change, infectious diseases, aging and public health. The Biomolecular Mass Spectrometry and Proteomics group is efficiently managing and storing very large amounts of raw data generated daily to the Dell DX Object Storage Platform powered by Caringo.

The Challenge

  • Big storage needs on a limited research budget
  • Long term deep archive requirements
  • Share and replicate data across existing CIFS network

The Solution

  • Leverage CAStor SDK for custom application integration
  • Use the power of metadata as a basis for future projects
  • Run on any standard commodity hardware for attractive ROI
  • Integrate with Active Directory for industry standard authentication
  • Built-in disaster recovery solution with no added cost

The Results

  • Metadata intelligence applied to enforcing data protection policies for a lifetime
  • Powerful new applications designed to harness custom metadata
  • Decreased cost of storage infrastructure by migrating to the Dell DX Object Storage Platform
  • Reduced management and administrative costs with self-managing, self-healing clusters
  • Surpass throughput SLAs with twice the speed for file access utilizing Caringo's CIFS integration
  • Expansion ready to seamlessly upgrade nodes and cluster capacity with no impact on production

The Configuration

  • Object storage cluster is configured as two (2) subclusters with half of the storage servers located in the lab and half in a remote data center for automatic disaster recovery without any added cost.
  • Lab spectrometers and research workstations seamlessly access storage over the existing CIFS network.
Caringo CAStor storage for education and research.