Sustainable and cost-effective long-term storage remains an unsolved problem. The most widely used storage technologies today are magnetic (hard disk drives and tape). They use media that degrades over time and has a limited lifetime, which leads to inefficient, wasteful, and costly solutions for storing long-lived data. We are building Silica: the first cloud storage system for archival data underpinned by quartz glass, an extremely resilient media with virtually unlimited lifetime. Data is written using ultrafast laser nano-structuring in the bulk of the glass, creating permanent modifications to the media that allows data to be left in situ indefinitely. Designing and building a new storage technology solely for the cloud affords us with a tremendous opportunity to completely re-think how storage systems are built, free from the legacy constraints of existing technologies. In Silica, we are co-designing and co-optimizing the entire system from the media & write/read processes all the way up to the cloud service level with sustainability and low-cost as primary objectives. Our design follows a cloud-first, data-driven approach underpinned by principles derived from analysing a real public cloud archival service. Here we discuss how these principles have shaped the Silica technology down to the laser nano-structuring process, ushering in a new era of sustainable, cost-effective storage.
The demand for long-term data storage in the cloud grows continuously into the zettabytes. Operating at such scales requires a fundamental re-thinking of how we build large-scale storage systems to archive data in a sustainable and costeffective manner. In Project Silica, a storage technology for the cloud is being designed and developed from the media up by leveraging the recent progress in ultrafast laser nano-structuring of the transparent media. Together with the advances in reading, decoding and error correction processes, high-density and high-throughput multi-dimensional volumetric optical data writing is achieved, enabling successful end-to-end proof-of-concept demonstrations of the technology. With exceptional media longevity, this could transform archival cloud storage. Here we briefly discuss the development of the technology, key metrics for cost-efficient optical data storage at scale, and successful proof-ofconcept demonstrations.
Optical switches represent an appealing option to address the upcoming scaling challenges facing electrical switches in data-center networks with the slowdown of Moore’s Law and the exponential increase in network demands posed by emerging cloud workloads. Wavelength switching based on tunable lasers and passive arrayed waveguide grating routers is a particularly promising technology for optical switching due to its amenability to fast switching and the passive nature of the core, which leads to lower power consumption and higher fault tolerance. We investigated the potential of this technology in the context of Sirius, a scalable, optically-switched network architecture for data centers, which can achieve ultra-fast switching time. At its core lies a novel tunable laser that can tune across wavelengths in less than 930 ps. The laser uses a disaggregated architecture where the carrier generation is separated from the wavelength tuning, which significantly reduces the wavelength tuning time compared to conventional tunable lasers. In this paper, we describe the different instantiations of this architecture that we developed and present the experimental evaluation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.