Linux Plumbers Conference

Kernel/Userspace/User Interfaces Microconference (Draft, Subject to Change)

One of the biggest secrets of FOSS's success is a well-crafted set of interfaces amongst the various components. Although famously not set in stone, these interfaces permit different FOSS projects to work for the most part separately, while still coming together as a coherent system. Such interfaces are clearly a key topic for the Linux Plumbers Conference.

Therefore, I am happy to announce that Jim Gettys, one of the original developers of the X Window System, past VP of Software at OLPC, now at Alcatel-Lucent Bell Labs, has selected a great lineup from a set of excellent submissions to the "Kernel/Userspace/User Interfaces" microconference.

Jim's first selection is "USB 3.0 for Linux" by Sarah Sharp. Thanks to Sarah, Linux is the first kernel to offer USB 3.0 support, adding yet another counter-example to the myth that Linux is late in supporting new devices. USB 3.0 promises high speed (5Gbps) and flexible power management (go green!), but being new, is still in development. This portion of the microconference will give an overview of USB 3.0 and provide a forum for discussing the inevitable USB 3.0 development issues.

Green computing is also key to Jim's second selection, "Power management: Communicating needs and desires" by Matthew Garrett. This portion of the microconference looks to raise the current power-management discussion beyond static policies to a more dynamic level that automatically takes the needs of userspace applications into account. Given that existing interfaces are not believed to be sufficient to support this sort of dynamic power management, we can expect a lively discussion.

Jim's final selection is "Checkpoint/Restart in Linux mainline" by Sukadev Bhattiprolu. Checkpoint/restart is the ability to save the state of a running application, then resume it later on a similar system. There are at least two out-of-tree checkpoint/restart implementations (Zap and OpenVZ), but the potential complexities of a full solution have deterred mainlining. Such complexities include network connections, graphical user interfaces, timed events, response-time constraints, and much more besides. So, if history is any guide, this discussion should generate significant excitement, and hopefully also creative solutions, restrictions, or reframings of the problems.

We hope to see you there!!!