[Xen-devel] [RFC Patch v2 00/45] COarse-grain LOck-stepping Virtual Machines for Non-stop Service

[Wen Congyang <wency@xxxxxxxxxxxxxx>]

Virtual machine (VM) replication is a well known technique for providing
application-agnostic software-implemented hardware fault tolerance -
"non-stop service". Currently, remus provides this function, but it buffers
all output packets, and the latency is unacceptable.

In xen summit 2012, We introduce a new VM replication solution: colo
(COarse-grain LOck-stepping virtual machine). The presentation is in
the following URL:
http://www.slideshare.net/xen_com_mgr/colo-coarsegrain-lockstepping-virtual-machines-for-nonstop-service

Here is the summary of the solution:
>From the client's point of view, as long as the client observes identical
responses from the primary and secondary VMs, according to the service
semantics, then the secondary vm is a valid replica of the primary
vm, and can successfully take over when a hardware failure of the
primary vm is detected.

This patchset is RFC, and implements the framework and disk replication of COLO:
1. Both primary vm and secondary vm are running
2. do checkoint
3. disk replication(use blktap2)

This patchset is based on remus-v18, and use migration v1. Only supports hvm
guest now.

TODO list:
1. Use migration v2 to implement COLO
3. nic replication
4. support pvm

Patch 1-3  : bugfix
Patch 4-11 : update some APIs which will be used by colo
Patch 12-15: temporarily update remus to reuse remus device codes
Patch 16-23: COLO framework related codes
Patch 24   : Hack patch, just for test
Patch 25-34: bugfix for blktap2
Patch 35-38: move some block-remus's codes to block-replication.c. These codes 
will
             be reused by COLO.
Patch 39   : implement block-colo
Patch 40-43: update libxl to support blktap2
Patch 44   : implement disk replication
Patch 45   : hypervisor bugfix. We find this bug before rebasing colo to newest 
xen.
             But we don't trigger this bug now.
Patch 46   : A patch for qemu-xen

Changlog from v1 to v2:
1. rebase to newest remus
2. add disk replication support

Hong Tao (1):
  copy the correct page to memory

Lai Jiangshan (1):
  colo: dynamic allocate aio_requests to avoid -EBUSY error

Wen Congyang (43):
  csum the correct page
  don't zero out ioreq page
  Refactor domain_suspend_callback_common()
  Update libxl__domain_resume() for colo
  Update libxl__domain_suspend_common_switch_qemu_logdirty() for colo
  Introduce a new internal API libxl__domain_unpause()
  Update libxl__domain_unpause() to support qemu-xen
  support to resume uncooperative HVM guests
  update datecopier to support sending data only
  introduce a new API to aync read data from fd
  move remus related codes to libxl_remus.c
  rename remus device to checkpoint device
  adjust the indentation
  don't touch remus in checkpoint_device
  Update libxl_save_msgs_gen.pl to support return data from xl to xc
  Allow slave sends data to master
  secondary vm suspend/resume/checkpoint code
  primary vm suspend/get_dirty_pfn/resume/checkpoint code
  xc_domain_save: flush cache before calling callbacks->postcopy() in
    colo mode
  COLO: xc related codes
  send store mfn and console mfn to xl before resuming secondary vm
  implement the cmdline for COLO
  HACK: do checkpoint per 20ms
  fix memory leak in block-remus
  pass uuid to the callback td_open
  return the correct dev path
  blktap2: use correct way to get remus_image
  don't call client_flush() when switching to unprotected mode
  remus: fix bug in tdremus_close()
  blktap2: use correct way to get free event id
  blktap2: don't return negative event id
  blktap2: use correct way to define array.
  blktap2: connect to backup asynchronously
  switch to unprotected mode before closing
  blktap2: move async connect related codes to block-replication.c
  blktap2: move ramdisk related codes to block-replication.c
  block-colo: implement colo disk replication
  pass correct file to qemu if we use blktap2
  support blktap remus in xl
  support blktap colo in xl:
  update libxl__device_disk_from_xs_be() to support blktap device
  libxl/colo: setup and control disk replication for blktap2 backends
  x86/hvm: Always set pending event injection when loading VMC[BS]
    state.

 docs/man/xl.pod.1                                  |   11 +-
 tools/blktap2/drivers/Makefile                     |    5 +-
 tools/blktap2/drivers/block-aio.c                  |   41 +-
 tools/blktap2/drivers/block-cache.c                |    4 +-
 tools/blktap2/drivers/block-colo.c                 | 1151 ++++++++++++++++++
 tools/blktap2/drivers/block-log.c                  |    4 +-
 tools/blktap2/drivers/block-qcow.c                 |    5 +-
 tools/blktap2/drivers/block-ram.c                  |    5 +-
 tools/blktap2/drivers/block-remus.c                | 1266 +++++---------------
 tools/blktap2/drivers/block-replication.c          | 1116 +++++++++++++++++
 tools/blktap2/drivers/block-replication.h          |  217 ++++
 tools/blktap2/drivers/block-vhd.c                  |    5 +-
 tools/blktap2/drivers/scheduler.c                  |   33 +-
 tools/blktap2/drivers/tapdisk-control.c            |   17 +-
 tools/blktap2/drivers/tapdisk-disktype.c           |   21 +-
 tools/blktap2/drivers/tapdisk-disktype.h           |    3 +-
 tools/blktap2/drivers/tapdisk-interface.c          |   21 +-
 tools/blktap2/drivers/tapdisk-interface.h          |    1 +
 tools/blktap2/drivers/tapdisk-vbd.c                |    9 +
 tools/blktap2/drivers/tapdisk-vbd.h                |    1 +
 tools/blktap2/drivers/tapdisk.h                    |    3 +-
 tools/libxc/xc_domain_restore.c                    |   74 +-
 tools/libxc/xc_domain_save.c                       |   66 +-
 tools/libxc/xc_resume.c                            |   20 +-
 tools/libxc/xenguest.h                             |   40 +
 tools/libxl/Makefile                               |    5 +-
 tools/libxl/libxl.c                                |  148 ++-
 tools/libxl/libxl.h                                |    3 +-
 tools/libxl/libxl_aoutils.c                        |   81 +-
 tools/libxl/libxl_blktap2.c                        |   35 +
 ...xl_remus_device.c => libxl_checkpoint_device.c} |  221 ++--
 tools/libxl/libxl_colo.h                           |   48 +
 tools/libxl/libxl_colo_restore.c                   |  878 ++++++++++++++
 tools/libxl/libxl_colo_save.c                      |  628 ++++++++++
 tools/libxl/libxl_colo_save_disk_blktap2.c         |  216 ++++
 tools/libxl/libxl_create.c                         |  138 ++-
 tools/libxl/libxl_device.c                         |    6 +-
 tools/libxl/libxl_dm.c                             |   20 +-
 tools/libxl/libxl_dom.c                            |  565 ++++-----
 tools/libxl/libxl_internal.h                       |  309 +++--
 tools/libxl/libxl_netbuffer.c                      |  127 +-
 tools/libxl/libxl_noblktap2.c                      |   35 +
 tools/libxl/libxl_nonetbuffer.c                    |   14 +-
 tools/libxl/libxl_qmp.c                            |   10 +
 tools/libxl/libxl_remus.c                          |  335 ++++++
 tools/libxl/libxl_remus.h                          |   27 +
 tools/libxl/libxl_remus_disk_drbd.c                |   67 +-
 tools/libxl/libxl_save_callout.c                   |   37 +-
 tools/libxl/libxl_save_helper.c                    |   17 +
 tools/libxl/libxl_save_msgs_gen.pl                 |   74 +-
 tools/libxl/libxl_types.idl                        |   14 +-
 tools/libxl/libxl_utils.c                          |   23 +
 tools/libxl/libxl_utils.h                          |    1 +
 tools/libxl/libxlu_disk_l.l                        |    2 +
 tools/libxl/xl_cmdimpl.c                           |   54 +-
 tools/libxl/xl_cmdtable.c                          |    3 +-
 xen/arch/x86/hvm/svm/svm.c                         |   16 +-
 xen/arch/x86/hvm/vmx/vmx.c                         |   25 +-
 58 files changed, 6558 insertions(+), 1763 deletions(-)
 create mode 100644 tools/blktap2/drivers/block-colo.c
 create mode 100644 tools/blktap2/drivers/block-replication.c
 create mode 100644 tools/blktap2/drivers/block-replication.h
 rename tools/libxl/{libxl_remus_device.c => libxl_checkpoint_device.c} (41%)
 create mode 100644 tools/libxl/libxl_colo.h
 create mode 100644 tools/libxl/libxl_colo_restore.c
 create mode 100644 tools/libxl/libxl_colo_save.c
 create mode 100644 tools/libxl/libxl_colo_save_disk_blktap2.c
 create mode 100644 tools/libxl/libxl_remus.c
 create mode 100644 tools/libxl/libxl_remus.h

-- 
1.9.3


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel