Re: [PATCH 0/3] PCI: vmd: Reducing tail latency by affining to the storage stack

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Thu, 2019-11-07 at 07:42 -0800, hch@xxxxxxxxxxxxx wrote:
> On Thu, Nov 07, 2019 at 03:40:15PM +0000, Derrick, Jonathan wrote:
> > On Thu, 2019-11-07 at 07:37 -0800, hch@xxxxxxxxxxxxx wrote:
> > > On Thu, Nov 07, 2019 at 02:12:50PM +0000, Derrick, Jonathan wrote:
> > > > > How does this compare to simplify disabling VMD?
> > > > 
> > > > It's a moot point since Keith pointed out a few flaws with this set,
> > > > however disabling VMD is not an option for users who wish to
> > > > passthrough VMD
> > > 
> > > And why would you ever pass through vmd instead of the actual device?
> > > That just makes things go slower and adds zero value.
> > 
> > Ability to use physical Root Ports/DSPs/etc in a guest. Slower is
> > acceptable for many users if it fits within a performance window
> 
> What is the actual use case?  What does it enable that otherwise doesn't
> work and is actually useful?  And real use cases please and no marketing
> mumble jumble.

A cloud service provider might have several VMs on a single system and
wish to provide surprise hotplug functionality within the guests so
that they don't need to bring the whole server down or migrate VMs in
order to swap disks.




[Index of Archives]     [DMA Engine]     [Linux Coverity]     [Linux USB]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [Greybus]

  Powered by Linux