What is this paper about?
Whole System Persistence (WSP) is a concept that makes it possible to interrupt the power supply to a computer without losing the current computing state. The system hardware has sufficient capacity reserves to write all volatile data to permanent storage media as soon as the power supply is interrupted. This makes it possible to shorten the conventional processes of starting up and shutting down a computer in favor of faster suspend and resume operations.
What exactly was discovered?
In the context of server systems, WSP could enable machines that are only used occasionally to be switched on and off quickly. The paper examines several approaches to implementing WSP on such machines. It is found that main memory technologies such as NVM (non-volatile memory) are a key factor for an efficient implementation of WSP. The special feature of NVM memories is that they do not lose their data if the power supply is interrupted. The research data shows that with an NVM-based version of WSP, an improvement in system response time of up to 93% can be achieved compared to booting and loading application data from an SSD. This means that the time from booting the operating system to the point at which the computer can be used can be reduced by up to 93%. The suspend and resume times of WSP are in the order of ten milliseconds. In comparison, the conventional startup and shutdown of the operating system takes 50 to 70 seconds.
What does this mean for us?
In an ideal scenario, our computer could be switched on and off as effortlessly as a light bulb. Then even a power failure would have no adverse effect on the system as such, as a controlled shutdown would still be possible thanks to WSP. For machines that are only used occasionally, energy could be saved by switching them on and off quickly.
Where can we find out more about this?
T. Miemietz, V. Reusch, M. Roitzsch and H. Härtig: An NVM Performance Study Towards Whole System Persistence on Server Platforms. DIMES ’23: Proceedings of the 1st Workshop in Disruptive Memory System, Koblenz. https://dl.acm.org/doi/10.1145/3609308.3625269
– – – – – –
Further links
👉 www.barkhauseninstitut.org
Photo: pixabay
