KVM and QEMU Internals- Understanding the IO Subsystem

This presentation will break down the plethora of options available for delivering storage to a virtual machine in KVM/QEMU. It will detail the mechanics and performance trade offs inherent in the different AIO modes, caching options, paravirtualization drivers, and thread settings. We will outline which OpenStack configuration options lead to the most desireable KVM/QEMU configuration settings, and what could be done to further enhance OpenStack's ability to take advantage of everything KVM/QEM.

From the perspective of the Compute service, the QEMU hypervisor is very similar to the KVM hypervisor. Both are controlled through libvirt, both support the same feature set, and all virtual machine images that are compatible with KVM are also compatible with QEMU. The main difference is that QEMU does not support native virtualization. Consequently, QEMU has worse performance than KVM and is a poor choice for a production deployment.

KVM: https://docs.openstack.org/mitaka/config-reference/compute/hypervisor-kvm.html
QEMU: https://docs.openstack.org/ocata/config-reference/compute/hypervisor-qemu.html

Speaker(s):
Kyle Bader

Connect with us:
OpenInfra Twitter: https://twitter.com/openinfradev
OpenInfra LinkedIn: https://www.linkedin.com/company/open-infrastructure-foundation/mycompany/
OpenInfra Facebook: https://www.facebook.com/openinfradev
OpenInfra Website: https://openinfra.dev/

#OpenInfra #OpenStack #OpenSource

Видео KVM and QEMU Internals- Understanding the IO Subsystem канала Open Infrastructure Foundation