Caringo Swarm™, Unified Storage Software unveiled

Caringo® has introduced a comprehensive approach to unified storage software, Caringo Swarm7, that leverages emergent behavior where all nodes follow simple rules to automatically manage complexity as the solution grows while supporting all major cloud, file and storage protocols for instant access and analysis.

What’s new:

Uncomplicated massive scaling through architectural innovations
• A new, patent-pending, dynamically distributed index in RAM that instantly locates and accesses objects using zero IOPS, reducing multicasting to a secondary role and reducing CPU load by 50% at nominal scale.
• Architectural optimizations increase single cluster scale to over a hundred petabytes
• Even faster post-problem recovery through rapid trimming.
• Faster rolling, no-downtime upgrades with a 300% decrease in node boot time
• True parallel uploads for massive object sizes.

Support for existing workloads and new use cases with unified storage interfaces
• Incorporates and leverages nearly a decade of experience with CAStor™, the pioneer of software-defined object storage.
• Caringo Swarm brings a shared pool of seamlessly scalable storage to the data center where customers can plug in the interface needed for any application use case.
• CloudScaler® for multi-tenant, S3-like storage, where users control security and performance behind their firewalls.
• FileScaler™ to support SMB and NFS file protocols on top of active archives with very large hierarchical namespaces.
• New BlockScaler™ for iSCSI support providing pure block over object - available in Q3
• All interfaces, including the existing CloudScaler that supports HTTP and S3 API access, write to Caringo Swarm. One storage infrastructure to support both legacy and true cloud applications.

Foundation for new data services through enhanced querying and Hadoop support
• Out-of-the-box Hadoop support. Caringo’s original and innovative approach implements a true read-only Hadoop file system, offering a high-bandwidth pipe straight from the storage cluster that entirely eliminates the separate ingest step from archive or filer into HDFS. HDFS may still be used to hold intermediate results.
• Enhanced metadata indexer to improve performance and scale for full metadata ad-hoc queries.
All-out attack on complexity, a shift to Caringo Swarm
• Swarm is the only way to ensure uncomplicated scaling of capacity and throughput, and eliminate the complexity associated with legacy storage systems. There are no-single points of failure, no specialty nodes and no vulnerable metadata databases. The same software appliance code runs on all nodes. Nodes may be heterogeneous in model, brand and capability; they can be added and retired in flight.