Gupta claims data durability of more than 99.9999999999 percent, while availability is over 99.99 percent. ![]() ![]() In addition, the company’s overheads can be reduced through hardware and software optimization of its storage needs.Īs far as the performance gains go, these are pretty impressive. Gupta says the advantages are twofold, because Dropbox can now boost performance by optimizing its in-house storage systems to eliminate the lag that comes with the public cloud. “It was clear to us from the beginning that we’d have to build everything from scratch, since there’s nothing in the open source community that’s proven to work reliably at our scale.” “We knew we’d be building one of only a handful of exabyte-scale storage systems in the world,” Gupta said. Last October, Dropbox achieved its goal of shifting 90 percent of its data to its in-house infrastructure. However, Dropbox’s massive growth prompted the company to begin building its own storage infrastructure back in 2013, and this was up and running by early 2015. “As the needs of our users and customers kept growing, we decided to invest seriously in building our own in-house storage system,” he said, adding that Dropbox has always used a hybrid architecture, with metadata and Web services kept in-house, and file content usually stored on Amazon’s cloud. ![]() Gupta revealed that Dropbox was one of the earliest adopters of Amazon’s S3 service to store bulk data, but that now its was handling more than 90 percent of its own storage needs. “We’re excited to announce that we’re now storing and serving over 90 percent of our users’ data on our custom-built infrastructure,” Dropbox VP of Engineering Akhil Gupta said in a blog post Monday. built the world’s most popular file sharing and storage service on the back of Amazon Web Service’s cloud infrastructure, but after years hosting its services in the cloud, it’s now using its own technology instead.
0 Comments
Leave a Reply. |