OpenIO has been founded in 2015 by Laurent Denel and six co-founders, to offer an object storage solution for building hyper-scalable IT infrastructures for a wide range of applications. OpenIO leverages open source software, developed since 2006, which is based on a grid technology that enables dynamic behaviors and supports heterogenous hardware. In October 2017 OpenIO completed a $5 million funding round. In October 2019, OpenIO announced that it had crossed the terabit per second barrier by benchmarking an infrastructure provided by Criteo. In July 2020, OVH acquired OpenIO to co-create an alternative European Object Storage solution on the market.
Product
OpenIO is a software-defined object storage solution that supports S3 and can be deployed on-premises, cloud-hosted or at the edge, on any hardware mix. It has been designed from the beginning for performance and cost-efficiency at any scale, and it has been optimized for Big Data, HPC and AI. OpenIO stores objects within in a flat structure within a massively distributed directory with indirections, this allows the data query path to be independent of the number of nodes and the performance not to be affected by the growth of the capacity. Servers are organized as a grid of nodes massively distributed, where each node takes part in directory and storage services, which ensures that there is no single point of failure and that new nodes are automatically discovered and immediately available without the need to rebalance data. The software is built on top of ConsciousGrid, a technology that ensures optimal data placement based on real-time metrics and allows the addition or removal of storage devices with automatic performance and load impact optimization. For data protection OpenIO has synchronous and asynchronous replication with multiple copies, and an erasure coding implementation based on Reed-Solomon that can be deployed in one data center or geo-distributed or stretched clusters. The software has a GridForApps feature that catches all events that occur in the cluster and can pass them up in the stack or to applications running on OpenIO nodes. This enables event-driven computing directly into the storage infrastructure. OpenIO has native objectAPIs and SDKs for Python, C and Java, it integrates a HTTPREST/API and has strong compatibility with the Amazon S3 API and the OpenStack Swift API. The company also offers a proprietaryFile System connector to access data stored in an OpenIO object store through file access methods: it is based on FUSE and presents a POSIX File System which can be shared over local networks via NFS, SMB and FTP. OpenIO is compatible with x86 and ARMv7/ARMv8 servers running Linux and has low hardware requirements, it can be installed also on Raspberry Pis and on storage drives with embedded server. The open source code is available on and it is licensed under AGPL3 for server code and LGPL3 for client code.
Performance
OpenIO claims to have reached 1.372 Tbps write speed on a cluster of 350 physical machines. The benchmark scenario, conducted under production conditions with standard hardware, consisted in backing upa 38PBHadoopdatalake via the DistCp command. This level of performance marks, according to analysts, the arrival of a new generation of object storage technologies oriented toward high performance and hyper-scalability.
