* zhanghailiang (zhang.zhanghaili...@huawei.com) wrote:
> Signed-off-by: zhanghailiang <zhang.zhanghaili...@huawei.com>
> Signed-off-by: Gao feng <gaof...@cn.fujitsu.com>
> ---
> include/net/colo-nic.h | 3 ++-
> migration/colo.c | 22 ++++++++++++++++++----
> net/colo-nic.c | 19 +++++++++++++++++++
> 3 files changed, 39 insertions(+), 5 deletions(-)
>
> diff --git a/include/net/colo-nic.h b/include/net/colo-nic.h
> index 67c9807..ddc21cd 100644
> --- a/include/net/colo-nic.h
> +++ b/include/net/colo-nic.h
> @@ -20,5 +20,6 @@ void colo_add_nic_devices(NetClientState *nc);
> void colo_remove_nic_devices(NetClientState *nc);
>
> int colo_proxy_compare(void);
> -
> +int colo_proxy_failover(void);
> +int colo_proxy_checkpoint(void);
> #endif
> diff --git a/migration/colo.c b/migration/colo.c
> index 579aabf..874971c 100644
> --- a/migration/colo.c
> +++ b/migration/colo.c
> @@ -94,6 +94,11 @@ static void slave_do_failover(void)
> ;
> }
>
> + if (colo_proxy_failover() != 0) {
> + error_report("colo proxy failed to do failover");
> + }
> + colo_proxy_destroy(COLO_SECONDARY_MODE);
I'm not sure if this is the best thing to do on a secondary failover.
If I understand correctly, when it's running, we have:
-------+
| br0---eth0
|
slave +-tun - xt_SECCOLO - br1---eth1
|
-------+
what I think that colo-proxy-destroy is doing is rewiring that as:
-------+
| +--------------br0---eth0
| |
slave +-tun + br1---eth1
|
-------+
but now we've lost the sequence number adjustment data that
was held in xt_SECCOLO and so you are likely to break existing TCP
connections.
Also, I don't think colo-proxy-script is passed a flag to let it
know whether the reason it's doing a slave_uninstall is due to
a failover or a simple shutdown; and so it assumes it has
to do the rewire for a failover.
(Actually the script in the qemu repo is newer than the script in
the colo-proxy repo, that one doesn't have the rewire at all).
Dave
> +
> colo = NULL;
>
> if (!autostart) {
> @@ -115,7 +120,7 @@ static void master_do_failover(void)
> if (!colo_runstate_is_stopped()) {
> vm_stop_force_state(RUN_STATE_COLO);
> }
> -
> + colo_proxy_destroy(COLO_PRIMARY_MODE);
> if (s->state != MIG_STATE_ERROR) {
> migrate_set_state(s, MIG_STATE_COLO, MIG_STATE_COMPLETED);
> }
> @@ -245,6 +250,11 @@ static int do_colo_transaction(MigrationState *s,
> QEMUFile *control)
>
> qemu_fflush(trans);
>
> + ret = colo_proxy_checkpoint();
> + if (ret < 0) {
> + goto out;
> + }
> +
> ret = colo_ctl_put(s->file, COLO_CHECKPOINT_SEND);
> if (ret < 0) {
> goto out;
> @@ -387,8 +397,6 @@ out:
> qemu_bh_schedule(s->cleanup_bh);
> qemu_mutex_unlock_iothread();
>
> - colo_proxy_destroy(COLO_PRIMARY_MODE);
> -
> return NULL;
> }
>
> @@ -508,6 +516,12 @@ void *colo_process_incoming_checkpoints(void *opaque)
> goto out;
> }
>
> + ret = colo_proxy_checkpoint();
> + if (ret < 0) {
> + goto out;
> + }
> + DPRINTF("proxy begin to do checkpoint\n");
> +
> ret = colo_ctl_get(f, COLO_CHECKPOINT_SEND);
> if (ret < 0) {
> goto out;
> @@ -584,6 +598,7 @@ out:
> * just kill slave
> */
> error_report("SVM is going to exit!");
> + colo_proxy_destroy(COLO_SECONDARY_MODE);
> exit(1);
> } else {
> /* if we went here, means master may dead, we are doing failover */
> @@ -610,6 +625,5 @@ out:
>
> loadvm_exit_colo();
>
> - colo_proxy_destroy(COLO_SECONDARY_MODE);
> return NULL;
> }
> diff --git a/net/colo-nic.c b/net/colo-nic.c
> index 563d661..02a454d 100644
> --- a/net/colo-nic.c
> +++ b/net/colo-nic.c
> @@ -379,6 +379,25 @@ void colo_proxy_destroy(int side)
> cp_info.index = -1;
> colo_nic_side = -1;
> }
> +
> +int colo_proxy_failover(void)
> +{
> + if (colo_proxy_send(NULL, 0, COLO_FAILOVER) < 0) {
> + return -1;
> + }
> +
> + return 0;
> +}
> +
> +int colo_proxy_checkpoint(void)
> +{
> + if (colo_proxy_send(NULL, 0, COLO_CHECKPOINT) < 0) {
> + return -1;
> + }
> +
> + return 0;
> +}
> +
> /*
> do checkpoint: return 1
> error: return -1
> --
> 1.7.12.4
>
>
--
Dr. David Alan Gilbert / dgilb...@redhat.com / Manchester, UK
