Features/COLO
Summary
COLO-COarse Grain LOck Stepping
Paper: academia paper in SOCC 2013
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. The idea is presented in Xen summit 2012, and 2013, and academia paper in SOCC 2013. It's also presented in KVM forum 2013: 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/2014-09/msg04459.html
Wiki: http://wiki.qemu.org/Features/COLO
Github:(Checkout to latest colo branch)
* Copyright (c) 2015 HUAWEI TECHNOLOGIES CO.,LTD. * Copyright (c) 2015 FUJITSU LIMITED * Copyright (c) 2015 Intel Corporation
Components
- COLO Manager:
- COLO Controller - Modifications of save/restore flow (Refer to MacroCheckpointing).
- COLO Disk Manager - 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 ontext of primary VM 's image.
- and send it to secondary VM’s which makes sure the context of secondary VM's image is consentient with
- COLO Proxy
- We need an module to compare the packets returned by Primary VM and Secondary VM
- and decide whether to start a checkpoint according to some rules. It is a linux kernel module
- for host.
Current Status
- COLO Manager:
- COLO Controller/Frame (View on Github Checkout to latest colo branch, RFC patch has been posted(v3))
- COLO Disk Manager (RFC patch has been posted)
- COLO Proxy(View on Github)
Failover & Heartbeat
We provide a qmp command:
colo_lost_heartbeat
This command will tell COLO that heartbeat is lost. COLO will do some action accordingly.
External heartbeat modules can use this qmp command to communicatewith COLO. Users can choose whatever heartbeat implementation they want.
Failover rule:
TODO
Block replication
This is the COLO Disk Manager implementation. Please refer to http://wiki.qemu.org/Features/BlockReplication
How to test COLO
Hardware requirements
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 connected nic for each guest nic. If you don't have enouth directly connected nic, you can use vlan.
Network link topology
=================================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:
br0: 192.168.0.88
br1: no ip address
eth1: 192.168.1.88
eth2: 192.168.2.88
===========================after failover=====================================
+--------+
|client |
master (dead) +----+---+ slave (alive)
-------------------------+ | ---------------------------+
PVM | + | |
+-------+ +----[eth0]-----[switch]-----[eth0]-------+ |
|guest | +---+-+ | | +---+-+ |
| [tap0]--+ br0 | | | | br0 +--+ |
| | +-----+ [eth1]-----[forward]----[eth1] +-----+ | SVM |
+-------+ | | | +-------+|
| | +-----+ | | guest ||
[eth2]---[checkpoint]---[eth2] |br1 | +[tap0] ||
| | +-----+ | ||
| | +-------+|
-------------------------+ +--------------------------+
Test environment prepare
- Prepare host kernel
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.
- Proxy module
- proxy module is used for network packets compare.
# git clone https://github.com/gao-feng/colo-proxy.git # cd ./colo-proxy # make # make install
- Modified iptables
- We have add a new rule to iptables command.
- The corresponding patch is COLO-library_for_iptables-1.4.21.patch
It is based on version 1.4.21.
You can get iptables-1.4.21 from http://www.linuxfromscratch.org/blfs/view/stable/postlfs/iptables.html
- Modified arptables
- Please put patch add-MARK-target-support-for-arptables.patch to arptables v0.0.4 and then compile and install arptables
- Qemu colo
- Checkout the latest colo branch from https://github.com/coloft/qemu
# cd qemu # ./configure --target-list=x86_64-softmmu --enable-colo --enable-quorum # make
- Set Up the Bridge and network environment
- You must setup you network environment like above picture(Network link topology Normal).
In master, setup a bridge br0, using command brctl, like: # ifconfig eth0 down # ifconfig eth0 0.0.0.0 # brctl addbr br0 # brctl addif br0 eth0 # ifconfig br0 192.168.0.33 netmask 255.255.255.0 # 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).
- Qemu-ifup
- We need a script to bring up the TAP interface.
You can find this info from http://en.wikibooks.org/wiki/QEMU/Networking.
Master:
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
Test steps
- 1) load modeule
# modprobe nf_conntrack_colo # modprobe nf_conntrack_colo (Other colo module will be automatically loaded by script colo-proxy-script.sh) # modprobe xt_mark # modprobe kvm-intel
- 2) startup qemu
- Master side:
# x86_64-softmmu/qemu-system-x86_64 -machine pc-i440fx-2.3,accel=kvm,usb=off \
-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 if=virtio,driver=quorum,read-pattern=fifo,\
children.0.file.filename=/mnt/sdb/pure_IMG/redhat/redhat-7.0.img,children.0.driver=raw,\
children.1.file.driver=nbd+colo,\
children.1.file.host=192.168.2.8,\
children.1.file.port=8889,\
children.1.file.export=colo1,\
children.1.driver=raw,\
children.1.ignore-errors=on \
-vnc :7 -m 2048 -smp 2 -device piix3-usb-uhci -device usb-tablet -monitor stdio -S
Note: 1. NBD Client should not be the first child of quorum. 2. There should be only one NBD Client. 3. host is the secondary physical machine's hostname or IP 4. Each disk must have its own export name.
- Slave side:
# x86_64-softmmu/qemu-system-x86_64 -machine pc-i440fx-2.3,accel=kvm,usb=off \
-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 if=none,driver=raw,file=/mnt/sdb/pure_IMG/redhat/redhat-7.0.img,id=nbd_target1 \
-drive if=virtio,driver=qcow2+colo,file=/mnt/ramfs/active_disk.img,export=colo1,\
backing_reference.drive_id=nbd_target1,\
backing_reference.hidden-disk.file.filename=/mnt/ramfs/hidden_disk.img,\
backing_reference.hidden-disk.driver=qcow2,\
backing_reference.hidden-disk.allow-write-backing-file=on \
-vnc :7 -m 2048 -smp 2 -device piix3-usb-uhci -device usb-tablet -monitor stdio -incoming tcp:0:8888
Note:
1. The export name for the same disk must be the same in primary
and secondary QEMU command line
2. The qmp command nbd_server_start must be run before running the
qmp command migrate on primary QEMU
3. Don't use nbd_server_start's other options
4. Active disk, hidden disk and nbd target's length should be the
same.
5. It is better to put active disk and hidden disk in ramdisk.
- 3) On Secondary VM's QEMU monitor, run
(qemu) nbd_server_start 192.168.2.88:8889
- 4) on Primary VM's QEMU monitor, run following command:
(qemu) migrate_set_capability colo on (qemu) migrate tcp:192.168.2.88:8888
- 5) done
- You will see two runing VMs, whenever you make changes to PVM, SVM will be synced.
- 6) failover test
- You can kill SVM (PVM) and run 'colo_lost_heartbeat' in PVM's (SVM's) monitor 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>