Mill Computing, Inc. › Forums › The Mill › Architecture › Virtual Mills and cloud servers
- AuthorPosts
- #1843 |
Has the team given though to how the Mill might work in a cloud server virtual machine context? My though is hypervisor services for low level I/O, network, threading, etc. , while supervisor thread in a turf presents to application threads as if the supervisor thread were operating as ‘root’ on the hardware. Any threads that don’t ordinarily talk to hardware need never know they are part of a “VM”.
Hardware level virtualization, might work if the OS kernel can be directed by the loaded to use alternate addresses for “hardware”, the access traps being serviced by the hypervisor. This sounds less efficient than a VM OS that knows to call hypervisor services. The kernel might still need to know the limits of available turf, limiting options for a kernel built for bare metal running in a VM.
We haven’t put much thought into virtual machine on the Mill, in part because it would appear relatively easy. The Mill has no reserved ops and no supervisor state; all protection is via memory accessibility. Consequently it would seem that VMs arise naturally by replicating the All address space, which is easily done by tacking an ASID on the caches and some specRegs.
Of course, it’s the things that seem simple that are often the most trouble, and I would not be surprised to find that Mill VM is not that easy. But right now we are focused on getting plain vanilla cores to work; VM is on the roadmap, but not an immediate concern.
- AuthorPosts
You must be logged in to reply to this topic.