Difference between revisions of "Archived/Xen Roadmap/4.3"

From Xen
Line 13: Line 13:
   
 
<pre>
 
<pre>
  +
* PVH mode, domU (w/ Linux)
* Event channel scalability
 
  +
owner: mukesh@oracle
  +
status: ?
  +
  +
* PVH mode, dom0 (w/ Linux)
  +
owner: mukesh@oracle
  +
status: ?
  +
  +
* Event channel scalability
 
owner: attilio@citrix
 
owner: attilio@citrix
 
status: ?
 
status: ?
 
Increase limit on event channels (currently 1024 for 32-bit guests,
 
Increase limit on event channels (currently 1024 for 32-bit guests,
 
4096 for 64-bit guests)
 
4096 for 64-bit guests)
  +
  +
* ARM server port
  +
owner: ijc@citrix
  +
status: Core hypervisor patches accepted; Linux paches pending
   
 
* NUMA scheduler affinity
 
* NUMA scheduler affinity
  +
critical
 
owner: dario@citrix
 
owner: dario@citrix
  +
status: ?
   
 
* NUMA Memory migration
 
* NUMA Memory migration
 
owner: dario@citrix
 
owner: dario@citrix
  +
status: ?
 
* PVH mode, domU (w/ Linux)
 
owner: mukesh@oracle
 
 
* PVH mode, dom0 (w/ Linux)
 
owner: mukesh@oracle
 
 
* ARM server port
 
owner: ijc@citrix
 
   
 
* blktap3
 
* blktap3
owner: @citrix
+
owner: thanos@citrix
  +
status: ?
   
 
* Default to QEMU upstream
 
* Default to QEMU upstream
 
- qemu-based stubdom (Linux or BSD libc)
 
- qemu-based stubdom (Linux or BSD libc)
owner: anthony@citrix
+
owner: anthony@citrix
  +
status: ?
qemu-upstream needs a more fully-featured libc than exists in
 
  +
qemu-upstream needs a more fully-featured libc than exists in
minios. Either work on a minimalist linux-based stubdom with
 
  +
minios. Either work on a minimalist linux-based stubdom with
glibc, or port one of the BSD libcs to minios.
 
  +
glibc, or port one of the BSD libcs to minios.
   
 
- pci pass-thru
 
- pci pass-thru
owner: anthony@citrix
+
owner: anthony@citrix
  +
status: ?
   
 
* Persistent grants
 
* Persistent grants
 
owner: @citrix
 
owner: @citrix
  +
status: ?
   
 
* Multi-page blk rings
 
* Multi-page blk rings
 
- blkback in kernel (konrad@oracle, ?@intel)
 
- blkback in kernel (konrad@oracle, ?@intel)
 
- qemu blkback
 
- qemu blkback
  +
status: ?
   
 
* Multi-page net protocol
 
* Multi-page net protocol
 
owner: ?
 
owner: ?
  +
status: ?
 
expand the network ring protocol to allow multiple pages for
 
expand the network ring protocol to allow multiple pages for
 
increased throughput
 
increased throughput
Line 61: Line 73:
 
* Scalability: 16TiB of RAM
 
* Scalability: 16TiB of RAM
 
owner: jan@suse
 
owner: jan@suse
  +
status: ?
  +
  +
* libvirt integration
  +
owner: ?
  +
status: ?
  +
To begin with, we need someone to go and make some lists:
  +
- Features available in libvirt/KVM not available in libvirt/Xen
  +
- Features available in xl/Xen but not available in libvirt/Xen
   
 
* xl vm-{export,import}
 
* xl vm-{export,import}
 
owner: ?
 
owner: ?
  +
status: ?
 
Allow xl to import and export VMs to other formats; particularly
 
Allow xl to import and export VMs to other formats; particularly
 
ovf, perhaps the XenServer format, or more.
 
ovf, perhaps the XenServer format, or more.
Line 70: Line 91:
 
* xl USB pass-through for PV guests
 
* xl USB pass-through for PV guests
 
owner: ?
 
owner: ?
  +
status: ?
 
- Port the xend PV pass-through functionality to xl.
 
- Port the xend PV pass-through functionality to xl.
 
- Make sure qemu-based USB with qemu-upstream works
 
- Make sure qemu-based USB with qemu-upstream works
Line 80: Line 102:
 
* Rationalized backend scripts (incl. driver domains)
 
* Rationalized backend scripts (incl. driver domains)
 
owner: roger@citrix
 
owner: roger@citrix
  +
status: ?
   
 
* Linux console improvements
 
* Linux console improvements
Line 89: Line 112:
 
* CPUID-based idle (don't rely on ACPI info f/ dom0)
 
* CPUID-based idle (don't rely on ACPI info f/ dom0)
 
owner: jan@suse
 
owner: jan@suse
(done, to be submitted)
+
status: done, to be submitted
   
 
* Remove hardcoded mobprobe's in xencommons
 
* Remove hardcoded mobprobe's in xencommons
 
owner: ?
 
owner: ?
  +
status: ?
   
 
* Make storage migration possible
 
* Make storage migration possible
 
owner: ?
 
owner: ?
  +
status: ?
 
There needs to be a way, either via command-line or via some hooks,
 
There needs to be a way, either via command-line or via some hooks,
 
that someone can build a "storage migration" feature on top of libxl
 
that someone can build a "storage migration" feature on top of libxl
Line 102: Line 127:
 
* Full-VM snapshotting
 
* Full-VM snapshotting
 
owner: ?
 
owner: ?
  +
status: ?
 
Have a way of coordinating the taking and restoring of VM memory and
 
Have a way of coordinating the taking and restoring of VM memory and
 
disk snapshots. This would involve some investigation into the best
 
disk snapshots. This would involve some investigation into the best
Line 108: Line 134:
 
* VM Cloning
 
* VM Cloning
 
owner: ?
 
owner: ?
  +
status: May need review
 
Again, a way of coordinating the memory and disk aspects. Research
 
Again, a way of coordinating the memory and disk aspects. Research
 
into the best way to do this would probably go along with the
 
into the best way to do this would probably go along with the
 
snapshotting feature.
 
snapshotting feature.
 
* PV audio (audio for stubdom qemu)
 
owner: stefano.panella@citrix
 
   
 
* Memory: Replace PoD with paging mechanism
 
* Memory: Replace PoD with paging mechanism
 
owner: george@citrix
 
owner: george@citrix
  +
status: May need review
  +
  +
* PV audio (audio for stubdom qemu)
  +
owner: stefano.panella@citrix
  +
status: ?
   
 
* Managed domains?
 
* Managed domains?

Revision as of 16:42, 19 September 2012

Proposed timeline

We are planning on a 9-month release cycle. Based on that, below are our estimated dates:

  • Feature Freeze: 1 March, 2013
  • First RC: 15 April 2013
  • Release: 1 June 2013

The RCs and release will of course depend on stability and bugs, and will therefore be fairly unpredictable. The feature freeze may be slipped for especially important features which are near completion.

Feature list

Below is a list of features we're tracking for this release. If you have updates to a tracked feature you are working on, or are working on a feature and wish it to be tracked, please let me know.

* PVH mode, domU (w/ Linux)
  owner: mukesh@oracle
  status: ?

* PVH mode, dom0 (w/ Linux)
  owner: mukesh@oracle
  status: ?

* Event channel scalability
  owner: attilio@citrix
  status: ?
  Increase limit on event channels (currently 1024 for 32-bit guests,
  4096 for 64-bit guests)

* ARM server port
  owner: ijc@citrix
  status: Core hypervisor patches accepted; Linux paches pending

* NUMA scheduler affinity
  critical
  owner: dario@citrix
  status: ?

* NUMA Memory migration 
  owner: dario@citrix
  status: ?

* blktap3 
  owner: thanos@citrix
  status: ?

* Default to QEMU upstream
 - qemu-based stubdom (Linux or BSD libc)
   owner: anthony@citrix
   status: ?
   qemu-upstream needs a more fully-featured libc than exists in
   minios.  Either work on a minimalist linux-based stubdom with
   glibc, or port one of the BSD libcs to minios.

 - pci pass-thru 
   owner: anthony@citrix
   status: ? 

* Persistent grants 
  owner: @citrix
  status: ?

* Multi-page blk rings
 - blkback in kernel (konrad@oracle, ?@intel)
 - qemu blkback
  status: ?

* Multi-page net protocol
  owner: ?
  status: ?
  expand the network ring protocol to allow multiple pages for
  increased throughput

* Scalability: 16TiB of RAM
  owner: jan@suse
  status: ?

* libvirt integration
  owner: ?
  status: ?
  To begin with, we need someone to go and make some lists:
  - Features available in libvirt/KVM not available in libvirt/Xen
  - Features available in xl/Xen but not available in libvirt/Xen

* xl vm-{export,import}
  owner: ?
  status: ?
  Allow xl to import and export VMs to other formats; particularly
  ovf, perhaps the XenServer format, or more.
  

* xl USB pass-through for PV guests
  owner: ?
  status: ?
  - Port the xend PV pass-through functionality to xl.
  - Make sure qemu-based USB with qemu-upstream works
  - Upstream the Linux frontend/backend drivers 

* openvswitch toostack integration
  owner: roger@citrix
  status: Sample script posted by Bastian ("[RFC] openvswitch support script")

* Rationalized backend scripts (incl. driver domains)
  owner: roger@citrix
  status: ?

* Linux console improvements
  owner: jan@suse
  -EHCI debug port (done, to be submitted)
  -xHCI debug port
  -Firewire

* CPUID-based idle (don't rely on ACPI info f/ dom0)
  owner: jan@suse
  status: done, to be submitted

* Remove hardcoded mobprobe's in xencommons
  owner: ?
  status: ?

* Make storage migration possible
  owner: ?
  status: ?
  There needs to be a way, either via command-line or via some hooks,
  that someone can build a "storage migration" feature on top of libxl
  or xl.

* Full-VM snapshotting
  owner: ?
  status: ?
  Have a way of coordinating the taking and restoring of VM memory and
  disk snapshots.  This would involve some investigation into the best
  way to accomplish this.

* VM Cloning
  owner: ?
  status: May need review
  Again, a way of coordinating the memory and disk aspects.  Research
  into the best way to do this would probably go along with the
  snapshotting feature.

* Memory: Replace PoD with paging mechanism
  owner: george@citrix
  status: May need review

* PV audio (audio for stubdom qemu)
  owner: stefano.panella@citrix
  status: ?

* Managed domains?