Make sure master start block replication after slave's block replication started.
Signed-off-by: zhanghailiang <zhang.zhanghaili...@huawei.com> Signed-off-by: Wen Congyang <we...@cn.fujitsu.com> Signed-off-by: Li Zhijian <lizhij...@cn.fujitsu.com> Cc: Stefan Hajnoczi <stefa...@redhat.com> Cc: Kevin Wolf <kw...@redhat.com> Cc: Max Reitz <mre...@redhat.com> --- migration/colo.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ migration/migration.c | 6 +++++- 2 files changed, 54 insertions(+), 1 deletion(-) diff --git a/migration/colo.c b/migration/colo.c index ac16d61..52eb403 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -23,6 +23,8 @@ #include "net/net.h" #include "net/filter.h" #include "net/vhost_net.h" +#include "block/block.h" +#include "replication.h" static bool vmstate_loading; @@ -64,6 +66,7 @@ static void secondary_vm_do_failover(void) { int old_state; MigrationIncomingState *mis = migration_incoming_get_current(); + Error *local_err = NULL; /* Can not do failover during the process of VM's loading VMstate, Or * it will break the secondary VM. @@ -81,6 +84,11 @@ static void secondary_vm_do_failover(void) migrate_set_state(&mis->state, MIGRATION_STATUS_COLO, MIGRATION_STATUS_COMPLETED); + replication_stop_all(true, &local_err); + if (local_err) { + error_report_err(local_err); + } + if (!autostart) { error_report("\"-S\" qemu option will be ignored in secondary side"); /* recover runstate to normal migration finish state */ @@ -159,6 +167,11 @@ static void primary_vm_do_failover(void) error_report_err(local_err); } + replication_stop_all(true, &local_err); + if (local_err) { + error_report_err(local_err); + } + /* Notify COLO thread that failover work is finished */ qemu_sem_post(&s->colo_exit_sem); } @@ -317,6 +330,15 @@ static int colo_do_checkpoint_transaction(MigrationState *s, if (local_err) { goto out; } + + /* We call this API although this may do nothing on primary side. */ + qemu_mutex_lock_iothread(); + replication_do_checkpoint_all(&local_err); + qemu_mutex_unlock_iothread(); + if (local_err) { + goto out; + } + colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err); if (local_err) { goto out; @@ -483,6 +505,12 @@ static void colo_process_checkpoint(MigrationState *s) object_unref(OBJECT(bioc)); qemu_mutex_lock_iothread(); + replication_start_all(REPLICATION_MODE_PRIMARY, &local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + vm_start(); qemu_mutex_unlock_iothread(); trace_colo_vm_state_change("stop", "run"); @@ -576,6 +604,7 @@ static void colo_wait_handle_message(QEMUFile *f, int *checkpoint_request, case COLO_MESSAGE_GUEST_SHUTDOWN: qemu_mutex_lock_iothread(); vm_stop_force_state(RUN_STATE_COLO); + replication_stop_all(false, NULL); qemu_system_shutdown_request_core(); qemu_mutex_unlock_iothread(); /* @@ -645,6 +674,14 @@ void *colo_process_incoming_thread(void *opaque) goto out; } + qemu_mutex_lock_iothread(); + bdrv_invalidate_cache_all(&local_err); + replication_start_all(REPLICATION_MODE_SECONDARY, &local_err); + qemu_mutex_unlock_iothread(); + if (local_err) { + goto out; + } + colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY, &local_err); if (local_err) { @@ -725,6 +762,18 @@ void *colo_process_incoming_thread(void *opaque) goto out; } + replication_get_error_all(&local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + /* discard colo disk buffer */ + replication_do_checkpoint_all(&local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + vmstate_loading = false; qemu_mutex_unlock_iothread(); diff --git a/migration/migration.c b/migration/migration.c index 3358980..5b5971f 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -1679,7 +1679,11 @@ static void migration_completion(MigrationState *s, int current_active_state, if (!ret) { ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE); - if (ret >= 0) { + /* + * Don't mark the image with BDRV_O_INACTIVE flag if + * we will go into COLO stage later. + */ + if (ret >= 0 && !migrate_colo_enabled()) { ret = bdrv_inactivate_all(); } if (ret >= 0) { -- 1.8.3.1