[libvirt] [PATCH 0/6] conf: qemu: Introduce relaxed config validation

[John Ferlan]

On 05/17/2016 10:25 AM, Peter Krempa wrote:
> Recently I NACKed quite a few patches attempting to add checks to the post
> parse callback infrastructure that would inhbit configs from being loaded
> after daemon restart.
> 
> To solve this introduce a new infrastructure that will get called only on
> codepaths that define and start the config leaving the code paths that load
> configs untouched.
> 
> Peter Krempa (6):
>   conf: disk: Rename virDomainDiskDefValidate to
>     virDomainDiskDefParseValidate
>   qemu: driver: Fix function header alignment of some functions
>   conf: Introduce infrastructure to add config validation to define time
>   qemu: Move check that validates 'min_guarantee' to
>     qemuDomainDefValidate
>   conf: Move check that validates disk info to virDomainDefValidate
>   conf: Add validation infrastructure for device hot/cold plug
> 
>  src/conf/domain_conf.c   | 128 +++++++++++++++++++++++++++++++++++++++--------
>  src/conf/domain_conf.h   |  11 ++--
>  src/libvirt_private.syms |   3 +-
>  src/qemu/qemu_conf.h     |   2 +
>  src/qemu/qemu_domain.c   |  38 ++++++++++++++
>  src/qemu/qemu_domain.h   |   3 ++
>  src/qemu/qemu_driver.c   |  26 ++++++++--
>  src/qemu/qemu_process.c  |  19 ++++---
>  8 files changed, 190 insertions(+), 40 deletions(-)
> 

Well I see that patch 6 addresses the comments from patch 3 at least
from qemuAttach

The genesis of what is now virDomainDiskDefValidate was to attempt to
extract out one of the qemuCheckDiskConfig checks into an earlier
failure. Looking at that - I would think it would be a prime candidate
to become patch 7 (yeah, I know, patches welcome...).  Thinking about
that code though reminds me - virStorageTranslateDiskSourcePool would
need to be called...

I'm in favor of this, but figure a few more eyes on it can also help.

John