The data center is a series of networks. There are networks that connect servers to users and networks that connect storage to servers. Even within servers and storage there are networks to connect CPU to IO devices like flash drives…
The data center is a series of networks. There are networks that connect servers to users and networks that connect storage to servers. Even within servers and storage there are networks to connect CPU to IO devices like flash drives…
Modern workloads such as Hadoop, Kafka and machine learning are demanding in terms of the volume of data that must be processed, the speed at which that data much be processed, and the fact that their capacity and performance requirements…
Against the backdrop of Moore’s Law and ultra-low latency non-volatile memory express (NVMe) solid state drives, network speed and total capacity are increasingly the levers that make or break an application’s performance. Fibre Channel (FC) storage networking may be frequently…
NVMe (Non-Volatile Memory Express) flash drives thrust storage media from the position of the worst performing component of the data center to the best. The technology’s low latency however, exposes other bottlenecks that went previously undetected. The new storage performance…
Hyperscale architectures typically sacrifice resource efficiency for performance by using direct attached storage instead of a shared storage solution. That lost efficiency though, means the organization is spending money on excess compute, graphics processing units (GPUs) and storage capacity that…
Direct attached storage (DAS) is the default storage “infrastructure” for data intensive workloads like Elastic, Hadoop, Kafka and TensorFlow. The problem, as we detailed in the last blog, is using DAS creates a brittle, siloed environment. Compute nodes can’t be…