Features/COLO: Difference between revisions

From QEMU
(Add my contact info)
 
(169 intermediate revisions by 3 users not shown)
Line 1: Line 1:
= Summary =
= Feature Name =
COLO-COarse Grain LOck Stepping<br>
COarse-grained LOck-stepping Virtual Machines for Non-stop Service<br>
Paper: [http://www.socc2013.org/home/program/a3-dong.pdf?attredirects=0 academia paper in SOCC 2013]


= Background =
Virtual machine (VM) replication is a well known technique for providing application-agnostic software-implemented hardware fault
Virtual machine (VM) replication is a well known technique for providing application-agnostic software-implemented hardware fault
tolerance "non-stop service". COLO is a high availability solution. Both primary VM (PVM) and secondary VM (SVM) run in parallel. They
tolerance "non-stop service". COLO is a high availability solution. Both primary VM (PVM) and secondary VM (SVM) run in parallel. They
receive the same request from client, and generate response in parallel too. If the response packets from PVM and SVM are identical, they are
receive the same request from client, and generate response in parallel too. If the response packets from PVM and SVM are identical, they are
released immediately. Otherwise, a VM checkpoint (on demand) is conducted. The idea is presented in Xen summit 2012, and 2013,
released immediately. Otherwise, a VM checkpoint (on demand) is conducted.<br>
and academia paper in SOCC 2013. It's also presented in KVM forum 2013:
[http://www.linux-kvm.org/wiki/images/1/1d/Kvm-forum-2013-COLO.pdf Kvm-forum-2013-COLO.pdf]


There's also several RFC proposal posted to QEMU devel maillist:
:[http://lists.nongnu.org/archive/html/qemu-devel/2014-06/msg05567.html http://lists.nongnu.org/archive/html/qemu-devel/2014-06/msg05567.html]
:[http://lists.nongnu.org/archive/html/qemu-devel/2014-09/msg04459.html http://lists.nongnu.org/archive/html/qemu-devel/2014-09/msg04459.html]


Wiki[http://wiki.qemu.org/Features/COLO http://wiki.qemu.org/Features/COLO]<br>
= Feature authors =
Github:
* '''Name:''' Chen Zhang, Lukas Straub, Hailiang Zhang, Congyang Wen, Yong Wang, Guang Wang
:[https://github.com/coloft/qemu https://github.com/coloft/qemu]Checkout to latest colo branch
* ''' Email:''' zhangckid@gmail.com/chen.zhang@intel.com, lukasstraub2@web.de, zhang.zhanghailiang@huawei.com, wency@cn.fujitsu.com, wang.yongD@h3c.com, wang.guanga@h3c.com
:[https://github.com/macrosheep/qemu https://github.com/macrosheep/qemu]
:[https://github.com/gao-feng/colo-proxy.git https://github.com/gao-feng/colo-proxy.git]
* Copyright (c) 2015 HUAWEI TECHNOLOGIES CO.,LTD.
* Copyright (c) 2015 FUJITSU LIMITED
* Copyright (c) 2015 Intel Corporation


= Components =
= Architecture =
The architecture of COLO is shown in the bellow diagram.
It consists of a pair of networked physical nodes:
The primary node running the PVM, and the secondary node running the SVM
to maintain a valid replica of the PVM.
PVM and SVM execute in parallel and generate output of response packets for
client requests according to the application semantics.


* COLO Manager:
The incoming packets from the client or external network are received by the
** COLO Controller - Modifications of save/restore flow (Refer to [http://wiki.qemu.org/Features/MicroCheckpointing MacroCheckpointing]).
primary node, and then forwarded to the secondary node, so that Both the PVM
** COLO Disk Manager - When primary VM writes data into image, the colo disk manger captures this data<br>
and the SVM are stimulated with the same requests.
:: and send it to secondary VM’s which makes sure the context of secondary VM's image is consentient with<br>
:: the ontext of primary VM 's image.
* COLO Proxy
: We need an module to compare the packets returned by Primary VM and Secondary VM<br>
: and decide whether to start a checkpoint according to some rules. It is a linux kernel module<br>
: for host.


= Current Status =
COLO receives the outbound packets from both the PVM and SVM and compares them
* COLO Manager:
before allowing the output to be sent to clients.
** COLO Controller/Frame ([https://github.com/coloft/qemu View on Github] Checkout to latest colo branch, RFC patch has been posted(v3))
 
** COLO Disk Manager (RFC patch has been posted)
The SVM is qualified as a valid replica of the PVM, as long as it generates
* COLO Proxy([https://github.com/gao-feng/colo-proxy.git. View on Github])
identical responses to all client requests. Once the differences in the outputs
are detected between the PVM and SVM, COLO withholds transmission of the
outbound packets until it has successfully synchronized the PVM state to the SVM.
 
  Primary Node                                                              Secondary Node
+------------+  +-----------------------+      +------------------------+  +------------+
|            |  |      HeartBeat      +<----->+      HeartBeat        |  |            |
| Primary VM |  +-----------+-----------+      +-----------+------------+  |Secondary VM|
|            |              |                              |              |            |
|            |  +-----------|-----------+      +-----------|------------+  |            |
|            |  |QEMU  +---v----+      |      |QEMU  +----v---+        |  |            |
|            |  |      |Failover|      |      |      |Failover|        |  |            |
|            |  |      +--------+      |      |      +--------+        |  |            |
|            |  |  +---------------+  |      |  +---------------+    |  |            |
|            |  |  | VM Checkpoint +-------------->+ VM Checkpoint |    |  |            |
|            |  |  +---------------+  |      |  +---------------+    |  |            |
|Requests<--------------------------\ /-----------------\ /--------------------->Requests|
|            |  |                  ^ ^ |      |      | |              |  |            |
|Responses+---------------------\ /-|-|------------\ /-------------------------+Responses|
|            |  |              | | | | |      |  | |  | |              |  |            |
|            |  | +-----------+ | | | | |      |  | |  | | +----------+ |  |            |
|            |  | | COLO disk | | | | | |      |  | |  | | | COLO disk| |  |            |
|            |  | |  Manager +---------------------------->| Manager | |  |            |
|            |  | ++----------+ v v | | |      |  | v  v | +---------++ |  |            |
|            |  |  |+-----------+-+-+-++|      | ++-+--+-+---------+ |  |  |            |
|            |  |  ||  COLO Proxy    ||      | |  COLO Proxy   | |  |  |            |
|            |  |  || (compare packet  ||      | |(adjust sequence | |  |  |            |
|            |  |  ||and mirror packet)||      | |    and ACK)    | |  |  |            |
|            |  |  |+------------+---^-+|      | +-----------------+ |  |  |            |
+------------+  +-----------------------+      +------------------------+  +------------+
+------------+    |            |  |                                |    +------------+
| VM Monitor |    |            |  |                                |    | VM Monitor |
+------------+    |            |  |                                |    +------------+
+---------------------------------------+      +----------------------------------------+
|  Kernel        |            |  |  |      |  Kernel            |                  |
+---------------------------------------+      +----------------------------------------+
                    |            |  |                                |
    +--------------v+  +---------v---+--+      +------------------+ +v-------------+
    |  Storage    |  |External Network|      | External Network | |  Storage    |
    +---------------+  +----------------+      +------------------+ +--------------+


= Failover & Heartbeat =
= Components introduction =
We provide a qmp command:
<pre>colo_lost_heartbeat</pre>


This command will tell COLO that heartbeat is lost. COLO will do some action accordingly.
* HeartBeat (Not yet implemented)
: Runs on both the primary and secondary nodes, to periodically check platform
: availability. When the primary node suffers a hardware fail-stop failure,
: the heartbeat stops responding, the secondary node will trigger a failover
: as soon as it determines the absence.
* COLO Block Replication (Please refer to [http://wiki.qemu.org/Features/BlockReplication BlockReplication])
: When primary VM writes data into image, the colo disk manger captures this data<br>
: and send it to secondary VM’s which makes sure the context of secondary VM's image is consentient with<br>
: the context of primary VM 's image.
: The following is the image of block replication workflow:


External heartbeat modules can use this qmp command to communicatewith COLO. Users can choose whatever heartbeat implementation they want.
        +----------------------+            +------------------------+
        |Primary Write Requests|            |Secondary Write Requests|
        +----------------------+            +------------------------+
                  |                                      |
                  |                                      (4)
                  |                                      V
                  |                              /-------------\
                  |      Copy and Forward        |            |
                  |---------(1)----------+      | Disk Buffer |
                  |                      |      |            |
                  |                    (3)      \-------------/
                  |                speculative      ^
                  |                write through    (2)
                  |                      |          |
                  V                      V          |
          +--------------+          +----------------+
          | Primary Disk |          | Secondary Disk |
          +--------------+          +----------------+


Failover rule:<br>
    1) Primary write requests will be copied and forwarded to Secondary
TODO
      QEMU.
    2) Before Primary write requests are written to Secondary disk, the
      original sector content will be read from Secondary disk and
      buffered in the Disk buffer, but it will not overwrite the existing
      sector content (it could be from either "Secondary Write Requests" or
      previous COW of "Primary Write Requests") in the Disk buffer.
    3) Primary write requests will be written to Secondary disk.
    4) Secondary write requests will be buffered in the Disk buffer and it
      will overwrite the existing sector content in the buffer.


= Block replication =
* COLO framework: COLO Checkpoint/Failover Controller
This is the COLO Disk Manager implementation.
: Modifications of save/restore flow to realize continuous migration, to make sure the state of VM in Secondary side
Please refer to [http://wiki.qemu.org/Features/BlockReplication http://wiki.qemu.org/Features/BlockReplication]
: always be consistent with VM in Primary side.
* COLO Proxy:
: Delivers packets to Primary and Seconday, and then compare the reponse from both side. Then decide whether to
: start a checkpoint according to some rules.


= Installation =
  Primary qemu                                                          Secondary qemu
* Hardware requriements
+--------------------------------------------------------------+      +----------------------------------------------------------------+
There is at least one directly connected nic to forward the network requests from client
| +----------------------------------------------------------+ |      |  +-----------------------------------------------------------+ |
to secondary vm. The directly connected nic must not be used by any other
| |                                                          | |      |  |                                                          | |
purpose. If your guest has more than one nic, you should have directly
| |                        guest                            | |      |  |                        guest                             | |
connected nic for each guest nic. If you don't have enouth directly connected
| |                                                          | |      |  |                                                          | |
nic, you can use vlan.
| +-------^--------------------------+-----------------------+ |      |  +---------------------+--------+----------------------------+ |
* Checkout the latest colo branch on Github.
|        |                          |                        |      |                        ^        |                              |
<pre>
|        |                          |                        |      |                        |        |                              |
/*for example, the latest brach is colo_v0.99, the version may rapidly grows, please make sure you are using the latest branch*/
|        |  +------------------------------------------------------+  |                        |        |                              |
# git clone https://github.com/macrosheep/qemu
|netfilter|  |                      |                        |    |  |  netfilter            |        |                              |
# git checkout colo_v0.99
| +----------+ +----------------------------+                  |    |  |  +-----------------------------------------------------------+ |
</pre>
| |      |  |                      |      |        out      |    |  |  |                    |        |  filter excute order      | |
* configure and make:
| |      |  |          +-----------------------------+        |    |  |  |                    |        | +------------------->     | |
<pre>
| |      |  |          |            |      |        |        |    |  |  |                    |        |  TCP                      | |
# ./configure --target-list=x86_64-softmmu --enable-colo
| | +-----+--+-+  +-----v----+ +-----v----+ |pri +----+----+sec|    |  |  | +------------+  +---+----+---v+rewriter++  +------------+ | |
# make
| | |          |  |          | |          | |in  |        |in |    |  |  | |            |  |        |              |  |            | | |
</pre>
| | |  filter  |  |  filter  | |  filter  +------>  colo  <------+ +-------->  filter  +--> adjust |  adjust    +-->   filter  | | |
| | |  mirror  |  |redirector| |redirector| |    | compare |  |  |    |  | | redirector |  | ack    |  seq        |  | redirector | | |
| | |          |  |          | |          | |    |        |  |  |    |  | |            |  |        |              |  |            | | |
| | +----^-----+  +----+-----+ +----------+ |    +---------+  |  |    |  | +------------+  +--------+--------------+  +---+--------+ | |
| |      |  tx        |  rx          rx  |                  |  |    |  |            tx                        all      |  rx      | |
| |      |            |                    |                  |  |    |  +-----------------------------------------------------------+ |
| |      |            +--------------+    |                  |  |    |                                                  |            |
| |      |  filter excute order      |    |                  |  |    |                                                  |            |
| |      |  +---------------->       |    |                  |  +--------------------------------------------------------+            |
| +-----------------------------------------+                  |      |                                                                |
|        |                            |                        |      |                                                                |
+--------------------------------------------------------------+      +----------------------------------------------------------------+
          |guest receive              | guest send
          |                            |
+--------+----------------------------v------------------------+
|                                                              |                          NOTE: filter direction is rx/tx/all
|                        tap                                  |                          rx:receive packets sent to the netdev
|                                                              |                          tx:receive packets sent by the netdev
+--------------------------------------------------------------+
: In COLO-compare, we do packet comparing job.
: Packets coming from the primary char indev will be sent to outdev.
: Packets coming from the secondary char dev will be dropped after comparing.
: colo-comapre need two input chardev and one output chardev: primary_in=chardev1-id (source: primary send packet) secondary_in=chardev2-id (source: secondary send packet) outdev=chardev3-id


* Install COLO agent module:
*'''Note:
** Download [https://github.com/wencongyang/colo-agent COLO agent], and compile it, it is the kernel module, so copy the module to the directory /lib/modules/<version>/updates/, and run depmod.
: HeartBeat is not been realized, so you need to trigger failover process by using 'x-colo-lost-heartbeat' command.
<pre>
# git clone https://github.com/wencongyang/colo-agent
# cd colo-agent; make
# cp *.ko /lib/modules/<version>/updates/
# depmod
</pre>
= Network link topology: =
<pre>
=================================normal ======================================
                                +--------+
                                |client  |
        master                +----+---+                    slave
-------------------------+          |            + -------------------------+
  PVM                  |          +            |                          |
+-------+        +----[eth0]-----[switch]-----[eth0]---------+              |
|guest  |    +---+-+    |                        |      +---+-+            |
|    [tap0]--+ br0 |    |                        |      | br0 |            |
|      |    +-----+  [eth1]-----[forward]----[eth1]--+  +-----+    SVM    |
+-------+                |                        |    |            +-------+|
                        |                        |    |  +-----+  | guest ||
                      [eth2]---[checkpoint]---[eth2]  +--+br1  |-[tap0]    ||
                        |                        |      +-----+  |      ||
                        |                        |                +-------+|
-------------------------+                        +--------------------------+
e.g.
master:
br0: 192.168.0.33
eth1: 192.168.1.33
eth2: 192.168.2.33


slave:
= Current Status =
br0: 192.168.0.88
Have been merged in Qemu upstream (v4.0).
br1: no ip address
eth1: 192.168.1.88
eth2: 192.168.2.88
</pre>


= Test environment prepare: =
= How to setup/test COLO =
* Prepare host kernel
For automatically managed colo: [[Features/COLO/Managed HOWTO]]
<pre>
colo-proxy kernel module need cooperate with linux kernel.
You should put a kernel patch 'colo-patch-for-kernel.patch'
(It's based on linux kernel-3.19) which you can get from
https://github.com/gao-feng/colo-proxy.git
and then compile kernel and intall the new kernel.
</pre>


* Proxy module
For manual use of colo via qmp commands: [[Features/COLO/Manual HOWTO]]
** proxy module is used for network packets compare.
<pre>
# git clone https://github.com/gao-feng/colo-proxy.git
# cd ./colo-proxy
# make
# make install
</pre>
* Modified iptables
** We have add a new rule to iptables command.
** The corresponding patch is [https://github.com/gao-feng/colo-proxy/blob/master/COLO-library_for_iptables-1.4.21.patch COLO-library_for_iptables-1.4.21.patch]<br>
It is based on version 1.4.21. <br>
You can get iptables-1.4.21 from http://www.linuxfromscratch.org/blfs/view/stable/postlfs/iptables.html
* Qemu colo
** Checkout the latest colo branch from [https://github.com/coloft/qemu https://github.com/coloft/qemu]
<pre>
# cd qemu
# ./configure --target-list=x86_64-softmmu --enable-colo --enable-quorum
# make
</pre>


* Set Up the Bridge and network environment
= Heartbeat Service =
** You must setup you network environment like above picture.
COLO support internal and external heartbeat service, they both use same qemu interface(qmp or monitor commands).
For internal service, we introduce new Qemu module named Advanced Watch Dog for this job.
Advanced Watch Dog is an universal monitoring module on VMM side, it can be used to detect network down(VMM to guest, VMM to VMM, VMM to another remote server) and do previously set operation.
If you want to use it, please add "--enable-awd" when configure qemu.
In primary node:
<pre>
<pre>
In master, setup a bridge br0, using command brctl, like:
-monitor tcp::4445,server,nowait
# ifconfig eth0 down
-chardev socket,id=h1,host=3.3.3.3,port=9009,server,nowait
# ifconfig eth0 0.0.0.0
-chardev socket,id=heartbeat0,host=3.3.3.3,port=4445
# brctl addbr br0
-object iothread,id=iothread1
# brctl addif br0 eth0
-object advanced-watchdog,id=heart1,server=on,awd_node=h1,notification_node=heartbeat0,
# ifconfig br0 192.168.0.33 netmask 255.255.255.0
opt_script=colo_primary_opt_script,iothread=iothread1,pulse_interval=1000,timeout=5000
# ifconfig eth0 up
In slave, setup two bridge br0, br1, commands are same with above,
please note that br1 is linked to eth1(the forward nic).
</pre>
</pre>


* Qemu-ifup
colo_primary_opt_script:
** We need a script to bring up the TAP interface.
You can find this info from [http://en.wikibooks.org/wiki/QEMU/Networking http://en.wikibooks.org/wiki/QEMU/Networking].
<pre>
<pre>
Master:
x_colo_lost_heartbeat
root@master# cat /etc/qemu-ifup
#!/bin/sh
switch=br0
if [ -n "$1" ]; then
        ip link set $1 up
        brctl addif ${switch} $1
fi
Slave:
root@slave # cat /etc/qemu-ifup
#!/bin/sh
switch=br1  #in primary, switch is br0. in secondary switch is br1
if [ -n "$1" ]; then
        ip link set $1 up
        brctl addif ${switch} $1
fi
</pre>
</pre>


= Test steps =
In secondary node:


*# load modeule
<pre>
<pre>
# modprobe nf_conntrack_colo
-monitor tcp::4445,server,nowait
# modprobe nf_conntrack_colo (Other colo module will be automatically loaded by
-chardev socket,id=h1,host=3.3.3.3,port=9009,reconnect=1
script colo-proxy-script.sh)
-chardev socket,id=heart1,host=3.3.3.8,port=4445
# modprobe xt_mark
-object iothread,id=iothread1
# modprobe kvm-intel
-object advanced-watchdog,id=heart1,server=off,awd_node=h1,notification_node=he
art1,opt_script=colo_secondary_opt_script,iothread=iothread1,timeout=10000
</pre>
</pre>


*# startup qemu
colo_secondary_opt_script:
** master:
<pre>
<pre>
# qemu-system-x86_64 -enable-kvm -netdev tap,id=hn0,colo_script=./scripts/colo-proxy-script.sh,colo_nicname=eth1 \
nbd_server_stop
-device virtio-net-pci,id=net-pci0,netdev=hn0 -boot c -drive driver=quorum,read-pattern=first,children.0.file.filename=suse11_3.img,children.0.driver=raw,children.1.file.driver=nbd+colo,children.1.file.host=192.168.2.88,children.1.file.port=8889,children.1.file.export=colo1,children.1.driver=raw,if=virtio
x_colo_lost_heartbeat
-vnc :7 -m 2048 -smp 2 -device piix3-usb-uhci -device usb-tablet -monitor stdio -S
</pre>
** slave:
<pre>
# qemu-system-x86_64 -enable-kvm -netdev tap,id=hn0,colo_script=./scripts/colo-proxy-script.sh,colo_nicname=eth1
-device virtio-net-pci,id=net-pci0,netdev=hn0 -boot c -drive driver=blkcolo,export=colo1,backing.file.filename=suse11_3.img,backing.driver=raw,if=virtio
-vnc :7 -m 2048 -smp 2 -device piix3-usb-uhci -device usb-tablet -monitor stdio -incoming tcp:0:8888
</pre>
* On Secondary VM's QEMU monitor, run
<pre>
(qemu) nbd_server_start 192.168.2.88:8889
</pre>
* on Primary VM's QEMU monitor, run following command:
<pre>
(qemu) migrate_set_capability colo on
(qemu) migrate tcp:192.168.2.88:8888
</pre>
</pre>
This parts of code still under review.
https://github.com/zhangckid/qemu/tree/colo-with-awd19dec1
For external service, user can write service and policy itself, it detect network down, just need notify COLO service.


*# done
= Supporting documentation =
** You will see two runing VMs, whenever you make changes to PVM, SVM
The idea is presented in Xen summit 2012, 2013 and [https://static.sched.com/hosted_files/xensummit19/d0/Application%20Agnostic%20High%20Availability%20Solution%20On%20Hypervisor%20Level%20-%20V1.4.pdf 2019]
will be synced to PVM's state.
and [http://www.socc2013.org/home/program/a3-dong.pdf?attredirects=0 academia paper in SOCC 2013].


*# failover test:
It is also presented in  
** You can kill SVM (PVM) and run 'colo_lost_heartbeat' in PVM's (SVM's) monitor
[https://www.linux-kvm.org/images/1/1d/Kvm-forum-2013-COLO.pdf KVM forum 2013], [http://www.linux-kvm.org/images/0/01/01x07-Hongyang_Yang-Status_update_on_KVM-COLO.pdf KVM forum 2015] and [http://www.linux-kvm.org/images/a/af/03x08B-Hailang_Zhang-Status_Update_on_KVM-COLO_FT.pdf KVM forum2016]
at the same time, then PVM (SVM) will failover and client will not feel this
change.


* For Questions/Issues, please contact: Zhang Hailiang <zhang.zhanghailiang@huawei.com>;Yang Hongyang <yanghy@cn.fujitsu.com>; Wen Congyang <wency@cn.fujitsu.com>
= Future works =
: 1. Support continuously VM replication.
: 2. Support shared storage.
: 3. Develop the heartbeat part.
: 4. Reduce checkpoint VM’s downtime while do checkpoint.


= Links =
= Links =
* [http://wiki.xen.org/wiki/COLO_-_Coarse_Grain_Lock_Stepping COLO on Xen]
* [http://wiki.xen.org/wiki/COLO_-_Coarse_Grain_Lock_Stepping COLO on Xen]

Latest revision as of 18:38, 30 January 2023

Feature Name

COarse-grained LOck-stepping Virtual Machines for Non-stop Service

Background

Virtual machine (VM) replication is a well known technique for providing application-agnostic software-implemented hardware fault tolerance "non-stop service". COLO is a high availability solution. Both primary VM (PVM) and secondary VM (SVM) run in parallel. They receive the same request from client, and generate response in parallel too. If the response packets from PVM and SVM are identical, they are released immediately. Otherwise, a VM checkpoint (on demand) is conducted.


Feature authors

  • Name: Chen Zhang, Lukas Straub, Hailiang Zhang, Congyang Wen, Yong Wang, Guang Wang
  • Email: zhangckid@gmail.com/chen.zhang@intel.com, lukasstraub2@web.de, zhang.zhanghailiang@huawei.com, wency@cn.fujitsu.com, wang.yongD@h3c.com, wang.guanga@h3c.com

Architecture

The architecture of COLO is shown in the bellow diagram. It consists of a pair of networked physical nodes: The primary node running the PVM, and the secondary node running the SVM to maintain a valid replica of the PVM. PVM and SVM execute in parallel and generate output of response packets for client requests according to the application semantics.

The incoming packets from the client or external network are received by the primary node, and then forwarded to the secondary node, so that Both the PVM and the SVM are stimulated with the same requests.

COLO receives the outbound packets from both the PVM and SVM and compares them before allowing the output to be sent to clients.

The SVM is qualified as a valid replica of the PVM, as long as it generates identical responses to all client requests. Once the differences in the outputs are detected between the PVM and SVM, COLO withholds transmission of the outbound packets until it has successfully synchronized the PVM state to the SVM.

 Primary Node                                                              Secondary Node
+------------+  +-----------------------+       +------------------------+  +------------+
|            |  |       HeartBeat       +<----->+       HeartBeat        |  |            |
| Primary VM |  +-----------+-----------+       +-----------+------------+  |Secondary VM|
|            |              |                               |               |            |
|            |  +-----------|-----------+       +-----------|------------+  |            |
|            |  |QEMU   +---v----+      |       |QEMU  +----v---+        |  |            |
|            |  |       |Failover|      |       |      |Failover|        |  |            |
|            |  |       +--------+      |       |      +--------+        |  |            |
|            |  |   +---------------+   |       |   +---------------+    |  |            |
|            |  |   | VM Checkpoint +-------------->+ VM Checkpoint |    |  |            |
|            |  |   +---------------+   |       |   +---------------+    |  |            |
|Requests<--------------------------\ /-----------------\ /--------------------->Requests|
|            |  |                   ^ ^ |       |       | |              |  |            |
|Responses+---------------------\ /-|-|------------\ /-------------------------+Responses|
|            |  |               | | | | |       |  | |  | |              |  |            |
|            |  | +-----------+ | | | | |       |  | |  | | +----------+ |  |            |
|            |  | | COLO disk | | | | | |       |  | |  | | | COLO disk| |  |            |
|            |  | |   Manager +---------------------------->| Manager  | |  |            |
|            |  | ++----------+ v v | | |       |  | v  v | +---------++ |  |            |
|            |  |  |+-----------+-+-+-++|       | ++-+--+-+---------+ |  |  |            |
|            |  |  ||   COLO Proxy     ||       | |   COLO Proxy    | |  |  |            |
|            |  |  || (compare packet  ||       | |(adjust sequence | |  |  |            |
|            |  |  ||and mirror packet)||       | |    and ACK)     | |  |  |            |
|            |  |  |+------------+---^-+|       | +-----------------+ |  |  |            |
+------------+  +-----------------------+       +------------------------+  +------------+
+------------+     |             |   |                                |     +------------+
| VM Monitor |     |             |   |                                |     | VM Monitor |
+------------+     |             |   |                                |     +------------+
+---------------------------------------+       +----------------------------------------+
|   Kernel         |             |   |  |       |   Kernel            |                  |
+---------------------------------------+       +----------------------------------------+
                   |             |   |                                |
    +--------------v+  +---------v---+--+       +------------------+ +v-------------+
    |   Storage     |  |External Network|       | External Network | |   Storage    |
    +---------------+  +----------------+       +------------------+ +--------------+

Components introduction

  • HeartBeat (Not yet implemented)
Runs on both the primary and secondary nodes, to periodically check platform
availability. When the primary node suffers a hardware fail-stop failure,
the heartbeat stops responding, the secondary node will trigger a failover
as soon as it determines the absence.
When primary VM writes data into image, the colo disk manger captures this data
and send it to secondary VM’s which makes sure the context of secondary VM's image is consentient with
the context of primary VM 's image.
The following is the image of block replication workflow:
       +----------------------+            +------------------------+
       |Primary Write Requests|            |Secondary Write Requests|
       +----------------------+            +------------------------+
                 |                                       |
                 |                                      (4)
                 |                                       V
                 |                              /-------------\
                 |      Copy and Forward        |             |
                 |---------(1)----------+       | Disk Buffer |
                 |                      |       |             |
                 |                     (3)      \-------------/
                 |                 speculative      ^
                 |                write through    (2)
                 |                      |           |
                 V                      V           |
          +--------------+           +----------------+
          | Primary Disk |           | Secondary Disk |
          +--------------+           +----------------+
   1) Primary write requests will be copied and forwarded to Secondary
      QEMU.
   2) Before Primary write requests are written to Secondary disk, the
      original sector content will be read from Secondary disk and
      buffered in the Disk buffer, but it will not overwrite the existing
      sector content (it could be from either "Secondary Write Requests" or
      previous COW of "Primary Write Requests") in the Disk buffer.
   3) Primary write requests will be written to Secondary disk.
   4) Secondary write requests will be buffered in the Disk buffer and it
      will overwrite the existing sector content in the buffer.
  • COLO framework: COLO Checkpoint/Failover Controller
Modifications of save/restore flow to realize continuous migration, to make sure the state of VM in Secondary side
always be consistent with VM in Primary side.
  • COLO Proxy:
Delivers packets to Primary and Seconday, and then compare the reponse from both side. Then decide whether to
start a checkpoint according to some rules.
 Primary qemu                                                           Secondary qemu
+--------------------------------------------------------------+       +----------------------------------------------------------------+
| +----------------------------------------------------------+ |       |  +-----------------------------------------------------------+ |
| |                                                          | |       |  |                                                           | |
| |                        guest                             | |       |  |                        guest                              | |
| |                                                          | |       |  |                                                           | |
| +-------^--------------------------+-----------------------+ |       |  +---------------------+--------+----------------------------+ |
|         |                          |                         |       |                        ^        |                              |
|         |                          |                         |       |                        |        |                              |
|         |  +------------------------------------------------------+  |                        |        |                              |
|netfilter|  |                       |                         |    |  |   netfilter            |        |                              |
| +----------+ +----------------------------+                  |    |  |  +-----------------------------------------------------------+ |
| |       |  |                       |      |        out       |    |  |  |                     |        |  filter excute order       | |
| |       |  |          +-----------------------------+        |    |  |  |                     |        | +------------------->      | |
| |       |  |          |            |      |         |        |    |  |  |                     |        |   TCP                      | |
| | +-----+--+-+  +-----v----+ +-----v----+ |pri +----+----+sec|    |  |  | +------------+  +---+----+---v+rewriter++  +------------+ | |
| | |          |  |          | |          | |in  |         |in |    |  |  | |            |  |        |              |  |            | | |
| | |  filter  |  |  filter  | |  filter  +------>  colo   <------+ +-------->  filter   +--> adjust |   adjust     +-->   filter   | | |
| | |  mirror  |  |redirector| |redirector| |    | compare |   |  |    |  | | redirector |  | ack    |   seq        |  | redirector | | |
| | |          |  |          | |          | |    |         |   |  |    |  | |            |  |        |              |  |            | | |
| | +----^-----+  +----+-----+ +----------+ |    +---------+   |  |    |  | +------------+  +--------+--------------+  +---+--------+ | |
| |      |   tx        |   rx           rx  |                  |  |    |  |            tx                        all       |  rx      | |
| |      |             |                    |                  |  |    |  +-----------------------------------------------------------+ |
| |      |             +--------------+     |                  |  |    |                                                   |            |
| |      |   filter excute order      |     |                  |  |    |                                                   |            |
| |      |  +---------------->        |     |                  |  +--------------------------------------------------------+            |
| +-----------------------------------------+                  |       |                                                                |
|        |                            |                        |       |                                                                |
+--------------------------------------------------------------+       +----------------------------------------------------------------+
         |guest receive               | guest send
         |                            |
+--------+----------------------------v------------------------+
|                                                              |                          NOTE: filter direction is rx/tx/all
|                         tap                                  |                          rx:receive packets sent to the netdev
|                                                              |                          tx:receive packets sent by the netdev
+--------------------------------------------------------------+
In COLO-compare, we do packet comparing job.
Packets coming from the primary char indev will be sent to outdev.
Packets coming from the secondary char dev will be dropped after comparing.
colo-comapre need two input chardev and one output chardev: primary_in=chardev1-id (source: primary send packet) secondary_in=chardev2-id (source: secondary send packet) outdev=chardev3-id
  • Note:
HeartBeat is not been realized, so you need to trigger failover process by using 'x-colo-lost-heartbeat' command.

Current Status

Have been merged in Qemu upstream (v4.0).

How to setup/test COLO

For automatically managed colo: Features/COLO/Managed HOWTO

For manual use of colo via qmp commands: Features/COLO/Manual HOWTO

Heartbeat Service

COLO support internal and external heartbeat service, they both use same qemu interface(qmp or monitor commands). For internal service, we introduce new Qemu module named Advanced Watch Dog for this job. Advanced Watch Dog is an universal monitoring module on VMM side, it can be used to detect network down(VMM to guest, VMM to VMM, VMM to another remote server) and do previously set operation. If you want to use it, please add "--enable-awd" when configure qemu. In primary node:

-monitor tcp::4445,server,nowait
-chardev socket,id=h1,host=3.3.3.3,port=9009,server,nowait
-chardev socket,id=heartbeat0,host=3.3.3.3,port=4445
-object iothread,id=iothread1
-object advanced-watchdog,id=heart1,server=on,awd_node=h1,notification_node=heartbeat0,
opt_script=colo_primary_opt_script,iothread=iothread1,pulse_interval=1000,timeout=5000

colo_primary_opt_script:

x_colo_lost_heartbeat

In secondary node:

-monitor tcp::4445,server,nowait
-chardev socket,id=h1,host=3.3.3.3,port=9009,reconnect=1
-chardev socket,id=heart1,host=3.3.3.8,port=4445
-object iothread,id=iothread1
-object advanced-watchdog,id=heart1,server=off,awd_node=h1,notification_node=he
art1,opt_script=colo_secondary_opt_script,iothread=iothread1,timeout=10000

colo_secondary_opt_script:

nbd_server_stop
x_colo_lost_heartbeat

This parts of code still under review. https://github.com/zhangckid/qemu/tree/colo-with-awd19dec1

For external service, user can write service and policy itself, it detect network down, just need notify COLO service.

Supporting documentation

The idea is presented in Xen summit 2012, 2013 and 2019 and academia paper in SOCC 2013.

It is also presented in KVM forum 2013, KVM forum 2015 and KVM forum2016

Future works

1. Support continuously VM replication.
2. Support shared storage.
3. Develop the heartbeat part.
4. Reduce checkpoint VM’s downtime while do checkpoint.

Links