[RFC][PATCH 00/13] Kemari: VM synchronization mechanism for fault tolerance

[Yoshiaki Tamura <tamura.yoshiaki@lab.ntt.co.jp>]

Hi,

This patch series implements Kemari, an open-source virtual machine
synchronization mechanism for fault tolerance.  It offers a feasible approach
to fault tolerance that does not require the use of specific hardware or
modification of applications/OS.  Kemari aims to keep VMs transparently running
in times of hardware failures.  It transfers the state of the primary VM to the
secondary VM when the primary VM is about to send an event to devices such as
storage and networks.  Kemari is applicable to 32bit HVM with PV Drivers.  For
more information, please visit http://www.osrg.net/kemari/

Overview:

Kemari in VMM taps event channel, pauses the guest (not suspend), prepares for
transfer, and Kemari in userland transfers the guest.  On failover, Kemari on
the secondary restores the guest, and the backend drivers in dom0 set up the
backend rings from the state of the shared rings in the guest.

[01] xen: add ECS_TAP state to event channel
[02] xen: core Kemari code
[03] xend: change parameter type of xc_{set,get}_hvm_param
[04] xend: Kemari controller interface in libxc
[05] xend: Kemari sender in libxc
[06] xend: Kemari receiver libxc
[07] xend: add Kemari support to python
[08] xend: add dev state "Attached" to python
[09] linux: add XenbusStateAttached to xenbus
[10] linux: XenbusStateAttached handler for blkback
[11] linux: XenbusStateAttached handler for netback
[12] ioemu: use signal to save qemu state for Kemari
[13] ioemu: use shared region with to flip logdirty_bitmap

The patches can be applied to

xen, xend: xen-3.3-testing.hg c/s 18430:19201eebab16 linux: linux-2.6.18-xen.hg
c/s 707:e410857fd83c ioemu: qemu-xen-3.3-testing.git c/s
d489fcbef71a527076a0f9ab56a71d7a7846d5b3:

We'll also keep working to update the patches to the latest trees.
Could you please review the code? Any comments are appreciated.

Thanks,

Yoshi