Here is a summary with links to some of the most interesting talks:
Big picture and roadmaps
Daniel Berrange gave an excellent overview of libvirt and libguestfs. These two tools, along with other virt-tools like virt-v2v, form the user-visible toolkit and APIs around KVM. Anyone who needs to automate KVM or develop custom applications that integrate with KVM should learn about the work being done by the libvirt community to provide both APIs and tools for managing virtualizated guests.
Alon Levy's SPICE Roadmap talk explains how remote graphics, input, sound, and USB are being added to KVM. SPICE goes far beyond today's VNC server, which can only scrape screen updates and send them to the client. SPICE has a deeper insight into the graphics pipeline and is able to provide efficient remote displays. In addition, channels for input, sound, and USB pass-through promise to bring good desktop integration to KVM.
Subsystem status and plumbing
Fixing the USB Disaster explains the state of USB, where Gerd Hoffmann has been working to remove limitations and add support for the USB 2.0 standard. These much-needed improvements will allow USB pass-through to actually work across devices. In the past I've had mixed results when passing through VoIP handsets and consumer electronics devices. Thanks to Gerd's work, I'm hoping that USB pass-through will work more consistently in future releases.
Migration: One year later tells the story of live migration in KVM. Juan Quintela has been working on this area of QEMU. In part due to today's live migration support in the device model, it has been a struggle to provide working live migration as device emulation is extended or fixed. In particular it is a challenging problem to migration from an old qemu-kvm to a new one, and vice versa.
AMD IOMMU Version 2 covers the enhanced I/O Memory Management Unit from AMD. Joerg Roedel, who has been working on nested virtualization on AMD CPUs, presents the key features of this new IOMMU. It adds PCI ATS-based support for demand paging. This eliminates the need to lock guest memory when doing PCI pass-through, since it's now possible to swap in a page and resume the I/O when a fault occurs.
Along the lines of Kemari, Kei Ohmura presents Rapid VM Synchronization with I/O Emulation Logging-Replay. The new trick is that I/O logging enables shared-nothing configurations where the primary and secondary host do not have access to shared storage. Instead the primary sends I/O logs to the secondary, where they are replayed to bring the secondary disk image up to date.
For a tour of performance tweaks across memory, networking, and storage, check out Mark Wagner's talk on KVM Performance Improvements and Optimizations. He covers Transparent Huge Pages, vhost-net, SR-IOV, block I/O schedulers, Linux AIO, NUMA tuning, and more.
Each talk was only 30 minutes long, and with two tracks that meant lots of talks. To see all presentations, go to the KVM Forum 2011 website.
This post only covered non-IBM presentations. There were so many IBMers working on KVM around that I'd like to bring together those talks and show all the areas they touch on. In my next post I will give an overview of the KVM presentations given by IBM Linux Technology Center people at KVM Forum and LinuxCon North America.