More Software Engineering Radio episodes

Bryan Cantrill on the Data Center Control Plane thumbnail

Bryan Cantrill on the Data Center Control Plane

Published 26 Feb 2026

Duration: 01:05:02

Building and scaling on-premises cloud infrastructure is plagued by hardware and firmware issues, legacy component limitations, and operational complexity.

Episode Description

Bryan Cantrill, the co-founder and CTO of Oxide Computer company, speaks with host Jeremy Jung about challenges in deploying hardware on-premises at s...

Overview

The podcast examines the difficulties of constructing and expanding on-premises cloud infrastructure, focusing on how abstraction of hardware by software developers can lead to complex problems, as exemplified by Samsung's acquisition of Joyant for its cloud capabilities. Key challenges include hardware and firmware issues such as severe input/output latency caused by faulty Toshiba drives, illustrating the difficulty of managing large-scale integrated systems. It also addresses limitations in legacy server components, like Baseboard Management Controllers (BMCs), which present operational and security issues due to outdated, closed-source designs. The discussion contrasts the relative simplicity of public cloud platforms like AWS with the complexity of on-premises deployments, emphasizing the need for full control and integration across all system layers. Additionally, the importance of scalable control planes, the challenges of using JavaScript in large-scale systems, and the shift toward more reliable programming languages like Rust are explored, along with the advantages of using open-source tools in the development of modern cloud infrastructure.

Recent Episodes of Software Engineering Radio

13 Aug 2026 SE Radio 733: Max Corbridge on Securing AI Agents

"Explores AI agent security risks, focusing on prompt injection vulnerabilities, non-deterministic threats, and the need for dynamic monitoring and proactive defenses against evolving AI-specific attacks."

15 Jul 2026 Garth Mollett on AI Supply Chain Security

"Explores AI supply chain security challenges, including probabilistic outputs, data poisoning, and emerging threats, while emphasizing structured measures like model signing and isolation to mitigate risks."

More Software Engineering Radio episodes