Update Documentation
Subsystems (2)
A message that is not in the archive (sent off-list or not yet received): [email protected]
PATCH v2 1/3 Replication: Ignore requests after failover
After failover the Secondary side of replication shouldn't change state, because it now functions as our primary disk.
In replication_start, replication_do_checkpoint, replication_stop, ignore the request if current state is BLOCK_REPLICATION_DONE (sucessful failover) or BLOCK_REPLICATION_FAILOVER (failover in progres i.e. currently merging active and hidden images into the base image).
--- block/replication.c | 38 +++++++++++++++++++++++++++++++++++--- 1 file changed, 35 insertions(+), 3 deletions(-)
block/replication.c +35 -3
@@ -454,6 +454,17 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode,aio_context_acquire (aio_context); s = bs->opaque; +if (s->stage ==BLOCK_REPLICATION_DONE || + s->stage ==BLOCK_REPLICATION_FAILOVER ) { +/* +* This case happens when a secondary is promoted to primary. +* Ignore the request because the secondary side of replication +* doesn't have to do anything anymore. +*/ +aio_context_release (aio_context); +return ; + } +if (s->stage !=BLOCK_REPLICATION_NONE ) {error_setg (errp,"Block replication is running or done" );aio_context_release (aio_context);
@@ -529,8 +540,7 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, "Block device is in use by internal backup job"); top_bs =bdrv_lookup_bs (s->top_id, s->top_id,NULL ); -if (!top_bs || !bdrv_is_root_node (top_bs) || - !check_top_bs (top_bs, bs)) { +if (!top_bs || !check_top_bs (top_bs, bs)) {error_setg (errp,"No top_bs or it is invalid" );reopen_backing_file (bs, false,NULL );aio_context_release (aio_context);
@@ -577,6 +587,17 @@ static void replication_do_checkpoint(ReplicationState *rs, Error **errp)aio_context_acquire (aio_context); s = bs->opaque; +if (s->stage ==BLOCK_REPLICATION_DONE || + s->stage ==BLOCK_REPLICATION_FAILOVER ) { +/* +* This case happens when a secondary was promoted to primary. +* Ignore the request because the secondary side of replication +* doesn't have to do anything anymore. +*/ +aio_context_release (aio_context); +return ; + } +if (s->mode ==REPLICATION_MODE_SECONDARY ) {secondary_do_checkpoint (s, errp); }
@@ -593,7 +614,7 @@ static void replication_get_error(ReplicationState *rs, Error **errp)aio_context_acquire (aio_context); s = bs->opaque; -if (s->stage !=BLOCK_REPLICATION_RUNNING ) { +if (s->stage ==BLOCK_REPLICATION_NONE ) {error_setg (errp,"Block replication is not running" );aio_context_release (aio_context);return ;
@@ -635,6 +656,17 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp)aio_context_acquire (aio_context); s = bs->opaque; +if (s->stage ==BLOCK_REPLICATION_DONE || + s->stage ==BLOCK_REPLICATION_FAILOVER ) { +/* +* This case happens when a secondary was promoted to primary. +* Ignore the request because the secondary side of replication +* doesn't have to do anything anymore. +*/ +aio_context_release (aio_context); +return ; + } +if (s->stage !=BLOCK_REPLICATION_RUNNING ) {error_setg (errp,"Block replication is not running" );aio_context_release (aio_context);
--
2.20.1
Re: [Qemu-devel] [PATCH v2 1/3] Replication: Ignore requests after failover
Quoted 9 lines · * Lukas Straub ([email protected]) wrote:
After failover the Secondary side of replication shouldn't change state, because it now functions as our primary disk.
In
replication_start,replication_do_checkpoint,replication_stop, ignore the request if current state isBLOCK_REPLICATION_DONE(sucessful failover) orBLOCK_REPLICATION_FAILOVER(failover in progres i.e. currently merging active and hidden images into the base image).Signed-off-by Lukas Straub <[email protected]>
We should add some block people to this one to review it; cc'ing in Kevin and Max.
Dave
Quoted 82 lines
--- block/replication.c | 38 +++++++++++++++++++++++++++++++++++--- 1 file changed, 35 insertions(+), 3 deletions(-)block/replication.c +35
-4@@ -454,6 +454,17 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode,aio_context_acquire (aio_context); s = bs->opaque; +if (s->stage ==BLOCK_REPLICATION_DONE || + s->stage ==BLOCK_REPLICATION_FAILOVER ) { +/* +* This case happens when a secondary is promoted to primary. +* Ignore the request because the secondary side of replication +* doesn't have to do anything anymore. +*/ +aio_context_release (aio_context); +return ; + } +if (s->stage !=BLOCK_REPLICATION_NONE ) {error_setg (errp,"Block replication is running or done" );aio_context_release (aio_context);@@ -529,8 +540,7 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, "Block device is in use by internal backup job"); top_bs =bdrv_lookup_bs (s->top_id, s->top_id,NULL ); -if (!top_bs || !bdrv_is_root_node (top_bs) || - !check_top_bs (top_bs, bs)) { +if (!top_bs || !check_top_bs (top_bs, bs)) {error_setg (errp,"No top_bs or it is invalid" );reopen_backing_file (bs, false,NULL );aio_context_release (aio_context);@@ -577,6 +587,17 @@ static void replication_do_checkpoint(ReplicationState *rs, Error **errp)aio_context_acquire (aio_context); s = bs->opaque; +if (s->stage ==BLOCK_REPLICATION_DONE || + s->stage ==BLOCK_REPLICATION_FAILOVER ) { +/* +* This case happens when a secondary was promoted to primary. +* Ignore the request because the secondary side of replication +* doesn't have to do anything anymore. +*/ +aio_context_release (aio_context); +return ; + } +if (s->mode ==REPLICATION_MODE_SECONDARY ) {secondary_do_checkpoint (s, errp); }@@ -593,7 +614,7 @@ static void replication_get_error(ReplicationState *rs, Error **errp)aio_context_acquire (aio_context); s = bs->opaque; -if (s->stage !=BLOCK_REPLICATION_RUNNING ) { +if (s->stage ==BLOCK_REPLICATION_NONE ) {error_setg (errp,"Block replication is not running" );aio_context_release (aio_context);return ;@@ -635,6 +656,17 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp)aio_context_acquire (aio_context); s = bs->opaque; +if (s->stage ==BLOCK_REPLICATION_DONE || + s->stage ==BLOCK_REPLICATION_FAILOVER ) { +/* +* This case happens when a secondary was promoted to primary. +* Ignore the request because the secondary side of replication +* doesn't have to do anything anymore. +*/ +aio_context_release (aio_context); +return ; + } +if (s->stage !=BLOCK_REPLICATION_RUNNING ) {error_setg (errp,"Block replication is not running" );aio_context_release (aio_context); --
Quoted 3 lines
2.20.1
--
Dr. David Alan Gilbert / [email protected] / Manchester, UK
PATCH v2 2/3 net/filter.c: Add Options to insert filters anywhere in the filter list
In reply to a message not in the archiveTo switch the Secondary to Primary, we need to insert new filters before the filter-rewriter.
Add the options insert= and position= to be able to insert filters anywhere in the filter list.
position should be either "head", "tail" or the id of another filter. insert should be either "before" or "after" to specify where to insert the new filter relative to the one specified with position.
--- include/net/filter.h | 2 ++ net/filter.c | 71 +++++++++++++++++++++++++++++++++++++++++++- qemu-options.hx | 10 +++---- 3 files changed, 77 insertions(+), 6 deletions(-)
include/net/filter.h +2 -0
@@ -62,6 +62,8 @@ struct NetFilterState {NetClientState *netdev;NetFilterDirection direction;bool on; +char *position; +bool insert_before;QTAILQ_ENTRY (NetFilterState) next; };
net/filter.c +70 -1
111 lines not on this page · raw message
qemu-options.hx +5 -5
@@ -4368,7 +4368,7 @@ applications, they can do this through this parameter. Its format is a gnutls priority string as described at @url{https://gnutls.org/manual/html_node/Priority-Strings.html}. -@item -object filter-buffer,id=@var{id},netdev=@var{netdevid},interval=@var{t}[,queue=@var{all|rx|tx}][,status=@var{on|off}] +@item -object filter-buffer,id=@var{id},netdev=@var{netdevid},interval=@var{t}[,queue=@var{all|rx|tx}][,status=@var{on|off}][,position=@var{head|tail|id}][,insert=@var{after|before}] Interval @var{t} can't be 0, this filter batches the packet delivery: all packets arriving in a given interval on netdev @var{netdevid} are delayed
@@ -4387,11 +4387,11 @@ queue @var{all|rx|tx} is an option that can be applied to any netfilter. @option{tx}: the filter is attached to the transmit queue of the netdev, where it will receive packets sent by the netdev. -@item -object filter-mirror,id=@var{id},netdev=@var{netdevid},outdev=@var{chardevid},queue=@var{all|rx|tx}[,vnet_hdr_support] +@item -object filter-mirror,id=@var{id},netdev=@var{netdevid},outdev=@var{chardevid},queue=@var{all|rx|tx}[,vnet_hdr_support][,position=@var{head|tail|id}][,insert=@var{after|before}] filter-mirror on netdev @var{netdevid},mirror net packet to chardev@var{chardevid}, if it has the vnet_hdr_support flag, filter-mirror will mirror packet with vnet_hdr_len. -@item -object filter-redirector,id=@var{id},netdev=@var{netdevid},indev=@var{chardevid},outdev=@var{chardevid},queue=@var{all|rx|tx}[,vnet_hdr_support] +@item -object filter-redirector,id=@var{id},netdev=@var{netdevid},indev=@var{chardevid},outdev=@var{chardevid},queue=@var{all|rx|tx}[,vnet_hdr_support][,position=@var{head|tail|id}][,insert=@var{after|before}] filter-redirector on netdev @var{netdevid},redirect filter's net packet to chardev @var{chardevid},and redirect indev's packet to filter.if it has the vnet_hdr_support flag,
@@ -4400,7 +4400,7 @@ Create a filter-redirector we need to differ outdev id from indev id, id can not be the same. we can just use indev or outdev, but at least one of indev or outdev need to be specified. -@item -object filter-rewriter,id=@var{id},netdev=@var{netdevid},queue=@var{all|rx|tx},[vnet_hdr_support] +@item -object filter-rewriter,id=@var{id},netdev=@var{netdevid},queue=@var{all|rx|tx},[vnet_hdr_support][,position=@var{head|tail|id}][,insert=@var{after|before}] Filter-rewriter is a part of COLO project.It will rewrite tcp packet to secondary from primary to keep secondary tcp connection,and rewrite
@@ -4413,7 +4413,7 @@ colo secondary: -object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1 -object filter-rewriter,id=rew0,netdev=hn0,queue=all -@item -object filter-dump,id=@var{id},netdev=@var{dev}[,file=@var{filename}][,maxlen=@var{len}] +@item -object filter-dump,id=@var{id},netdev=@var{dev}[,file=@var{filename}][,maxlen=@var{len}][,position=@var{head|tail|id}][,insert=@var{after|before}] Dump the network traffic on netdev @var{dev} to the file specified by @var{filename}. At most @var{len} bytes (64k by default) per packet are stored.
--
2.20.1
PATCH v2 3/3 Update Documentation
In reply to a message not in the archiveDocument the qemu command-line and qmp commands for continious replication
--- docs/COLO-FT.txt | 185 +++++++++++++++++++++++++++++++++++------------ 1 file changed, 138 insertions(+), 47 deletions(-)
docs/COLO-FT.txt +138 -47
@@ -145,35 +145,64 @@ The diagram just shows the main qmp command, you can get the detail in test procedure. == Test procedure == +Note: Here we are running both instances on the same Machine for testing, +change the IP Addresses if you want to run it on two Hosts + 1. Startup qemu Primary: -# qemu-system-x86_64 -accel kvm -m 2048 -smp 2 -qmp stdio -name primary \ - -device piix3-usb-uhci -vnc :7 \ - -device usb-tablet -netdev tap,id=hn0,vhost=off \ - -device virtio-net-pci,id=net-pci0,netdev=hn0 \ - -drive if=virtio,id=primary-disk0,driver=quorum,read-pattern=fifo,vote-threshold=1,\ - children.0.file.filename=1.raw,\ - children.0.driver=raw -S +# imagefolder="/mnt/vms/colo-test" + +# cp --reflink=auto $imagefolder/primary.qcow2 $imagefolder/primary-copy.qcow2 + +# qemu-system-x86_64 -enable-kvm -cpu qemu64,+kvmclock -m 512 -smp 1 -qmp stdio \ + -vnc :0 -k de -device piix3-usb-uhci -device usb-tablet -name primary \ + -netdev tap,id=hn0,vhost=off,helper=/usr/lib/qemu/qemu-bridge-helper \ + -device rtl8139,id=e0,netdev=hn0 \ + -chardev socket,id=mirror0,host=127.0.0.1,port=9003,server,nowait \ + -chardev socket,id=compare1,host=127.0.0.1,port=9004,server,wait \ + -chardev socket,id=compare0,host=127.0.0.1,port=9001,server,nowait \ + -chardev socket,id=compare0-0,host=127.0.0.1,port=9001 \ + -chardev socket,id=compare_out,host=127.0.0.1,port=9005,server,nowait \ + -chardev socket,id=compare_out0,host=127.0.0.1,port=9005 \ + -object filter-mirror,id=m0,netdev=hn0,queue=tx,outdev=mirror0 \ + -object filter-redirector,netdev=hn0,id=redire0,queue=rx,indev=compare_out \ + -object filter-redirector,netdev=hn0,id=redire1,queue=rx,outdev=compare0 \ + -object iothread,id=iothread1 \ + -object colo-compare,id=comp0,primary_in=compare0-0,secondary_in=compare1,\ +outdev=compare_out0,iothread=iothread1 \ + -drive if=ide,id=colo-disk0,driver=quorum,read-pattern=fifo,vote-threshold=1,\ +children.0.file.filename=$imagefolder/primary.qcow2,children.0.driver=qcow2 -S + Secondary: -# qemu-system-x86_64 -accel kvm -m 2048 -smp 2 -qmp stdio -name secondary \ - -device piix3-usb-uhci -vnc :7 \ - -device usb-tablet -netdev tap,id=hn0,vhost=off \ - -device virtio-net-pci,id=net-pci0,netdev=hn0 \ - -drive if=none,id=secondary-disk0,file.filename=1.raw,driver=raw,node-name=node0 \ - -drive if=virtio,id=active-disk0,driver=replication,mode=secondary,\ - file.driver=qcow2,top-id=active-disk0,\ - file.file.filename=/mnt/ramfs/active_disk.img,\ - file.backing.driver=qcow2,\ - file.backing.file.filename=/mnt/ramfs/hidden_disk.img,\ - file.backing.backing=secondary-disk0 \ - -incoming tcp:0:8888 +# imagefolder="/mnt/vms/colo-test" + +# qemu-img create -f qcow2 $imagefolder/secondary-active.qcow2 10G + +# qemu-img create -f qcow2 $imagefolder/secondary-hidden.qcow2 10G + +# qemu-system-x86_64 -enable-kvm -cpu qemu64,+kvmclock -m 512 -smp 1 -qmp stdio \ + -vnc :1 -k de -device piix3-usb-uhci -device usb-tablet -name secondary \ + -netdev tap,id=hn0,vhost=off,helper=/usr/lib/qemu/qemu-bridge-helper \ + -device rtl8139,id=e0,netdev=hn0 \ + -chardev socket,id=red0,host=127.0.0.1,port=9003,reconnect=1 \ + -chardev socket,id=red1,host=127.0.0.1,port=9004,reconnect=1 \ + -object filter-redirector,id=f1,netdev=hn0,queue=tx,indev=red0 \ + -object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1 \ + -object filter-rewriter,id=rew0,netdev=hn0,queue=all \ + -drive if=none,id=parent0,file.filename=$imagefolder/primary-copy.qcow2,driver=qcow2 \ + -drive if=none,id=childs0,driver=replication,mode=secondary,file.driver=qcow2,\ +top-id=childs0,file.file.filename=$imagefolder/secondary-active.qcow2,\ +file.backing.driver=qcow2,file.backing.file.filename=$imagefolder/secondary-hidden.qcow2,\ +file.backing.backing=parent0 \ + -drive if=ide,id=colo-disk0,driver=quorum,read-pattern=fifo,vote-threshold=1,\ +children.0.file=childs0,children.0.driver=raw \ + -incoming tcp:0:9998 + 2. On Secondary VM's QEMU monitor, issue command {'execute':'qmp_capabilities'} -{ 'execute': 'nbd-server-start', - 'arguments': {'addr': {'type': 'inet', 'data': {'host': 'xx.xx.xx.xx', 'port': '8889'} } } -} -{'execute': 'nbd-server-add', 'arguments': {'device': 'secondary-disk0', 'writable': true } } +{'execute': 'nbd-server-start', 'arguments': {'addr': {'type': 'inet', 'data': {'host': '127.0.0.1', 'port': '9999'} } } } +{'execute': 'nbd-server-add', 'arguments': {'device': 'parent0', 'writable': true } } Note: a. The qmp command nbd-server-start and nbd-server-add must be run
@@ -184,12 +213,10 @@ Note: 3. On Primary VM's QEMU monitor, issue command: {'execute':'qmp_capabilities'} -{ 'execute': 'human-monitor-command', - 'arguments': {'command-line': 'drive_add -n buddy driver=replication,mode=primary,file.driver=nbd,file.host=xx.xx.xx.xx,file.port=8889,file.export=secondary-disk0,node-name=nbd_client0'}} -{ 'execute':'x-blockdev-change', 'arguments':{'parent': 'primary-disk0', 'node': 'nbd_client0' } } -{ 'execute': 'migrate-set-capabilities', - 'arguments': {'capabilities': [ {'capability': 'x-colo', 'state': true } ] } } -{ 'execute': 'migrate', 'arguments': {'uri': 'tcp:xx.xx.xx.xx:8888' } } +{'execute': 'human-monitor-command', 'arguments': {'command-line': 'drive_add -n buddy driver=replication,mode=primary,file.driver=nbd,file.host=127.0.0.1,file.port=9999,file.export=parent0,node-name=replication0'}} +{'execute': 'x-blockdev-change', 'arguments':{'parent': 'colo-disk0', 'node': 'replication0' } } +{'execute': 'migrate-set-capabilities', 'arguments': {'capabilities': [ {'capability': 'x-colo', 'state': true } ] } } +{'execute': 'migrate', 'arguments': {'uri': 'tcp:127.0.0.1:9998' } } Note: a. There should be only one NBD Client for each primary disk.
@@ -199,27 +226,91 @@ Note: 4. After the above steps, you will see, whenever you make changes to PVM, SVM will be synced. You can issue command '{ "execute": "migrate-set-parameters" , "arguments":{ "x-checkpoint-delay": 2000 } }' -to change the checkpoint period time +to change the idle checkpoint period time 5. Failover test -You can kill Primary VM and run 'x_colo_lost_heartbeat' in Secondary VM's -monitor at the same time, then SVM will failover and client will not detect this -change. +You can kill one of the VMs and Failover on the surviving VM: -Before issuing '{ "execute": "x-colo-lost-heartbeat" }' command, we have to -issue block related command to stop block replication. -Primary: - Remove the nbd child from the quorum: - { 'execute': 'x-blockdev-change', 'arguments': {'parent': 'colo-disk0', 'child': 'children.1'}} - { 'execute': 'human-monitor-command','arguments': {'command-line': 'drive_del blk-buddy0'}} - Note: there is no qmp command to remove the blockdev now +== Primary Failover == +The Secondary died, resume on the Primary -Secondary: - The primary host is down, so we should do the following thing: - { 'execute': 'nbd-server-stop' } +{'execute': 'x-blockdev-change', 'arguments':{ 'parent': 'colo-disk0', 'child': 'children.1'} } +{'execute': 'human-monitor-command', 'arguments':{ 'command-line': 'drive_del replication0' } } +{'execute': 'object-del', 'arguments':{ 'id': 'comp0' } } +{'execute': 'object-del', 'arguments':{ 'id': 'iothread1' } } +{'execute': 'object-del', 'arguments':{ 'id': 'm0' } } +{'execute': 'object-del', 'arguments':{ 'id': 'redire0' } } +{'execute': 'object-del', 'arguments':{ 'id': 'redire1' } } +{'execute': 'x-colo-lost-heartbeat' } + +== Secondary Failover == +The Primary died, resume on the Secondary and prepare to become the new Primary + +{'execute': 'nbd-server-stop'} +{'execute': 'x-colo-lost-heartbeat'} + +{'execute': 'object-del', 'arguments':{ 'id': 'f2' } } +{'execute': 'object-del', 'arguments':{ 'id': 'f1' } } +{'execute': 'chardev-remove', 'arguments':{ 'id': 'red1' } } +{'execute': 'chardev-remove', 'arguments':{ 'id': 'red0' } } + +{'execute': 'chardev-add', 'arguments':{ 'id': 'mirror0', 'backend': {'type': 'socket', 'data': {'addr': { 'type': 'inet', 'data': { 'host': '127.0.0.1', 'port': '9003' } }, 'server': true } } } } +{'execute': 'chardev-add', 'arguments':{ 'id': 'compare1', 'backend': {'type': 'socket', 'data': {'addr': { 'type': 'inet', 'data': { 'host': '127.0.0.1', 'port': '9004' } }, 'server': true } } } } +{'execute': 'chardev-add', 'arguments':{ 'id': 'compare0', 'backend': {'type': 'socket', 'data': {'addr': { 'type': 'inet', 'data': { 'host': '127.0.0.1', 'port': '9001' } }, 'server': true } } } } +{'execute': 'chardev-add', 'arguments':{ 'id': 'compare0-0', 'backend': {'type': 'socket', 'data': {'addr': { 'type': 'inet', 'data': { 'host': '127.0.0.1', 'port': '9001' } }, 'server': false } } } } +{'execute': 'chardev-add', 'arguments':{ 'id': 'compare_out', 'backend': {'type': 'socket', 'data': {'addr': { 'type': 'inet', 'data': { 'host': '127.0.0.1', 'port': '9005' } }, 'server': true } } } } +{'execute': 'chardev-add', 'arguments':{ 'id': 'compare_out0', 'backend': {'type': 'socket', 'data': {'addr': { 'type': 'inet', 'data': { 'host': '127.0.0.1', 'port': '9005' } }, 'server': false } } } } + +== Primary resume replication == +Resume replication after new Secondary is up. + +Start the new Secondary, then: +{'execute': 'drive-mirror', 'arguments':{ 'device': 'colo-disk0', 'job-id': 'resync', 'target': 'nbd://127.0.0.1:9999/parent0', 'mode': 'existing', 'format': 'raw', 'sync': 'full'} } + +Wait until disk is synced, then: +{'execute': 'stop'} +{'execute': 'block-job-cancel', 'arguments':{ 'device': 'resync'} } + +{'execute': 'human-monitor-command', 'arguments':{ 'command-line': 'drive_add -n buddy driver=replication,mode=primary,file.driver=nbd,file.host=127.0.0.1,file.port=9999,file.export=parent0,node-name=replication0'}} +{'execute': 'x-blockdev-change', 'arguments':{ 'parent': 'colo-disk0', 'node': 'replication0' } } + +{'execute': 'object-add', 'arguments':{ 'qom-type': 'filter-mirror', 'id': 'm0', 'props': { 'netdev': 'hn0', 'queue': 'tx', 'outdev': 'mirror0' } } } +{'execute': 'object-add', 'arguments':{ 'qom-type': 'filter-redirector', 'id': 'redire0', 'props': { 'netdev': 'hn0', 'queue': 'rx', 'indev': 'compare_out' } } } +{'execute': 'object-add', 'arguments':{ 'qom-type': 'filter-redirector', 'id': 'redire1', 'props': { 'netdev': 'hn0', 'queue': 'rx', 'outdev': 'compare0' } } } +{'execute': 'object-add', 'arguments':{ 'qom-type': 'iothread', 'id': 'iothread1' } } +{'execute': 'object-add', 'arguments':{ 'qom-type': 'colo-compare', 'id': 'comp0', 'props': { 'primary_in': 'compare0-0', 'secondary_in': 'compare1', 'outdev': 'compare_out0', 'iothread': 'iothread1' } } } + +{'execute': 'migrate-set-capabilities', 'arguments':{ 'capabilities': [ {'capability': 'x-colo', 'state': true } ] } } +{'execute': 'migrate', 'arguments':{ 'uri': 'tcp:127.0.0.1:9998' } } + +Note: +If this Primary previously was a Secondary, then we need to insert the +filters before the filter-rewriter by using the +"'insert': 'before', 'position': 'rew0'" Options. See below. + +== Secondary resume replication == +Become Primary and resume replication after new Secondary is up. + +Start the new Secondary, then: +{'execute': 'drive-mirror', 'arguments':{ 'device': 'colo-disk0', 'job-id': 'resync', 'target': 'nbd://127.0.0.1:9999/parent0', 'mode': 'existing', 'format': 'raw', 'sync': 'full'} } + +Wait until disk is synced, then: +{'execute': 'stop'} +{'execute': 'block-job-cancel', 'arguments':{ 'device': 'resync' } } + +{'execute': 'human-monitor-command', 'arguments':{ 'command-line': 'drive_add -n buddy driver=replication,mode=primary,file.driver=nbd,file.host=127.0.0.1,file.port=9999,file.export=parent0,node-name=replication0'}} +{'execute': 'x-blockdev-change', 'arguments':{ 'parent': 'colo-disk0', 'node': 'replication0' } } + +{'execute': 'object-add', 'arguments':{ 'qom-type': 'filter-mirror', 'id': 'm0', 'props': { 'insert': 'before', 'position': 'rew0', 'netdev': 'hn0', 'queue': 'tx', 'outdev': 'mirror0' } } } +{'execute': 'object-add', 'arguments':{ 'qom-type': 'filter-redirector', 'id': 'redire0', 'props': { 'insert': 'before', 'position': 'rew0', 'netdev': 'hn0', 'queue': 'rx', 'indev': 'compare_out' } } } +{'execute': 'object-add', 'arguments':{ 'qom-type': 'filter-redirector', 'id': 'redire1', 'props': { 'insert': 'before', 'position': 'rew0', 'netdev': 'hn0', 'queue': 'rx', 'outdev': 'compare0' } } } +{'execute': 'object-add', 'arguments':{ 'qom-type': 'iothread', 'id': 'iothread1' } } +{'execute': 'object-add', 'arguments':{ 'qom-type': 'colo-compare', 'id': 'comp0', 'props': { 'primary_in': 'compare0-0', 'secondary_in': 'compare1', 'outdev': 'compare_out0', 'iothread': 'iothread1' } } } + +{'execute': 'migrate-set-capabilities', 'arguments':{ 'capabilities': [ {'capability': 'x-colo', 'state': true } ] } } +{'execute': 'migrate', 'arguments':{ 'uri': 'tcp:127.0.0.1:9998' } } == TODO == -1. Support continuous VM replication. -2. Support shared storage. -3. Develop the heartbeat part. -4. Reduce checkpoint VM’s downtime while doing checkpoint. +1. Support shared storage. +2. Develop the heartbeat part. +3. Reduce checkpoint VM’s downtime while doing checkpoint.
Signature · 1 line
2.20.1