With the proliferation of new applications like Artificial Intelligence, Internet-of-Things, Big Data and Cloud Computing, today’s hyper-scale data centers run far more diversified and complex workloads than ever before.
These different applications can have drastically different I/O patterns, performance or Quality-of-Service (QoS) targets, usage models, and sometimes require a different set of features from storage devices.
Alibaba has announced the launch of a new system that aims to optimize the storage performance of hyper-scale infrastructure in addressing increasing demands from usage of artificial intelligence (AI) and cloud computing.
A Dual-mode SSD (Solid State Drive), a storage device which supports both Open-Channel Mode and native NVMe mode, has been developed by the Alibaba Infrastructure Services team, and an optimal software/hardware integrated solution based on the Dual-mode SSD is currently being deployed to Alibaba's internal servers.
It is expected this novel storage system will lead to a 75% reduction in reading latency and enhance the overall storage performance of data centers by as many as five times.
Alibaba Infrastructure Services senior staff engineer Shu Li says, "The increasing proliferation of AI and cloud computing has led to more sophisticated demands in data centers, while traditional storage systems face severe limitation in meeting such demands.
“Against this background, Alibaba has pioneered the research and development of a new storage system, the Dual-mode SSD infrastructure.”
“This underscores our commitment to driving the innovation and optimization of technology infrastructure in a new AI and cloud era.”
By creating and sharing the Dual-mode SSD specification, they are also working with different manufacturers on related firmware and hardware products, supposedly leading to the fast development of SSD-centered infrastructure and ecosystems.
Diversified workloads and fast-changing requirements in the hyperscale data center have deeply changed the demands for storage systems.
I/O architecture based on standard SSDs can no longer satisfy these demands, resulting in suboptimal performance. In this paper, we present a hardware/software co-design approach to pursue optimal storage performance.