From KVM
Revision as of 11:26, 15 December 2010 by Lmr (Talk | contribs)

KVM-Autotest TODO list

raw idea

  • more vhost_net test
  • Add Multi-guests transfer test
  • transfer test between guest(s) and extra boxs
  • add more whql tests (virtio_net,virtio_blk)


Note: This session is for major, multi-person items. We'll update the status weekly based on the status of the subtasks attributed to persons.

the kvm autotest wrapper properly on top of the parametrized control file feature, that is currently halfway implemented


    • Move kvm autotest libraries to client/bin directory, so every client side test can use
    • Review xen-autotest to see what are the differences between our vm class and theirs. Hopefully in the future, xen-autotest and libvirt-autotest will be only different vm implementations of our virt-autotest framework :)



  • Multi host migration - Already have a 1st patchset available, working to rebase it against a cleanup patchset made by Jason
  • Create 'maintenance jobs' just to keep the machines up to date, with appropriate software installed.
  • Hotplug tests during migration
  • Work on setting up the conmux server for our internal test grid
  • Research how to trigger jobs based on events rather than using the web interface setting recurrent jobs
  • Set up a qemu-block job, with kwolf's qemu-block tree
  • Set up a vhost job, with the upstream job (mst's trees for kernel and userspace)
  • Add a BLOCKED status on the autotest database, that tells the user that some feature testing was left out due to a problem on its dependencies.
  • Eventually get rid of all dependency on slirp/userspace networking to do any feature testing, since it is not a supported feature. Slipstreaming the kickstart in the install CD is a possibility, and it ends up being simpler than configuring an internal network thing for testing.
  • Make it possible to install virtio nw driver under windows xp/2003 guests without having to resort to the msi installer


  • Infrastructure for testing different vm storage backends: file/lvm/iSCSI - Done by Beijing team
  • Made some internal patches appropriate for upstream
  • Copy on the email list of results
  • Send code to retrieve host kernels based on koji/brew tags upstream
  • Resolved UUID mount point check problem
  • QMP suite integrated upstream
  • Wrote code to retrieve kernels based on koji/brew tags


  • Make WHQL tests run on our internal server
  • Enable "guest-load" for a VMs before/while tests are running (e.g. migration of a VM, while a movie is playing on it)
    • This may just be a matter of moving useful code from tests to to make it reusable


  • Post-commit review of new network patches (committed on Oct 7 2010)
  • Use more exceptions in utility functions:
    • Add convenience functions to to make running shell commands shorter
    • Add convenience functions to the VM class
  • Refactor _get_command_output() and friends in and add cmd_raw(), cmd_obj() and cmd_qmp() as required by Luiz Capitulino's test suite
  • Use select() instead of sleep() in
  • Simplify migration code if possible (in and
  • Fix VM.get_ifname() somehow (uses self.vnc_port -- bad)


  • push redhat internal kvm subtests(18) to upstream

  • Add a new test: check if guest transmits packets when link is up/down
  • Report problem with multiple NICs and MAC address tracking [problem fixed]
  • Using dnsmasq in unattended_install to replace userspace network with private bridge [request changed]
  • Bonding test [done]


  • Write a 'cli' wrapper to make autotest handy/easier for developers
  • Tests in parallel with migration (reboot/unattended installation/file transfer/ autotest client tests / guest_script,autoit? / memtest86+(steps?)), need modifications to framework?
  • Refactor hotplug test using qdev and netdev_del/drive_del
  • Refactor the network cmdline generation, using peer when possible and vlan for elder qemu-kvm
  • Port network tests into windows


  • Migration to exec test suggested by mst
  • Clean the Migration tests: mainly for exec and add offline support


  • Run netperf test between two guests
  • Migration with/without workload(dbench,lmbench etc)
  • Verify SMBIOS/DMI data (UUID, for example)
  • Disk serial number (for IDE, SCSI, VirtIO drives)

Beijing QE

  • pxe boot * net types
  • Further migration
  • Multiple nics
  • multiple disks
  • Test block device cancellation path using device mapper to generate errors ( after we had a crash in de_write_dma_cb)
  • Extend pci_assignable to support other PCI devices (USB, video cards, TV card etc)
  • Different CPU flags support
  • Passthrough the perf keys of run_autotest to autotest server
  • Register the virtual machine into autotest server and run benchmark through autotest server