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>
---
migration/colo.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
trace-events | 2 ++
2 files changed, 62 insertions(+)
diff --git a/migration/colo.c b/migration/colo.c
index b7a7ad6..d748fb5 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -21,6 +21,7 @@
#include "qapi-event.h"
#include "net/filter.h"
#include "net/net.h"
+#include "block/block_int.h"
static bool vmstate_loading;
@@ -55,6 +56,7 @@ 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.
@@ -72,6 +74,12 @@ static void secondary_vm_do_failover(void)
migrate_set_state(&mis->state, MIGRATION_STATUS_COLO,
MIGRATION_STATUS_COMPLETED);
+ bdrv_stop_replication_all(true, &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ }
+ trace_colo_stop_block_replication("failover");
+
if (!autostart) {
error_report("\"-S\" qemu option will be ignored in secondary side");
/* recover runstate to normal migration finish state */
@@ -107,6 +115,7 @@ static void primary_vm_do_failover(void)
{
MigrationState *s = migrate_get_current();
int old_state;
+ Error *local_err = NULL;
migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
MIGRATION_STATUS_COMPLETED);
@@ -134,6 +143,12 @@ static void primary_vm_do_failover(void)
qemu_set_default_filters_status(false);
/* Flush the residuary buffered packts */
qemu_release_default_filters_packets();
+
+ bdrv_stop_replication_all(true, &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ }
+ trace_colo_stop_block_replication("failover");
}
void colo_do_failover(MigrationState *s)
@@ -240,6 +255,7 @@ static int colo_do_checkpoint_transaction(MigrationState *s,
int colo_shutdown;
size_t size;
QEMUFile *trans = NULL;
+ Error *local_err = NULL;
ret = colo_put_cmd(s->to_dst_file, COLO_COMMAND_CHECKPOINT_REQUEST);
if (ret < 0) {
@@ -278,6 +294,16 @@ static int colo_do_checkpoint_transaction(MigrationState
*s,
goto out;
}
+ /* we call this api although this may do nothing on primary side */
+ qemu_mutex_lock_iothread();
+ bdrv_do_checkpoint_all(&local_err);
+ qemu_mutex_unlock_iothread();
+ if (local_err) {
+ error_report_err(local_err);
+ ret = -1;
+ goto out;
+ }
+
ret = colo_put_cmd(s->to_dst_file, COLO_COMMAND_VMSTATE_SEND);
if (ret < 0) {
goto out;
@@ -324,6 +350,10 @@ static int colo_do_checkpoint_transaction(MigrationState
*s,
qemu_release_default_filters_packets();
if (colo_shutdown) {
+ qemu_mutex_lock_iothread();
+ bdrv_stop_replication_all(false, NULL);
+ trace_colo_stop_block_replication("shutdown");
+ qemu_mutex_unlock_iothread();
colo_put_cmd(s->to_dst_file, COLO_COMMAND_GUEST_SHUTDOWN);
qemu_fflush(s->to_dst_file);
colo_shutdown_requested = 0;
@@ -378,6 +408,7 @@ static void colo_process_checkpoint(MigrationState *s)
QEMUSizedBuffer *buffer = NULL;
int64_t current_time, checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
int ret = 0;
+ Error *local_err = NULL;
failover_init_state();
ret = colo_init_buffer_filters();
@@ -414,6 +445,15 @@ static void colo_process_checkpoint(MigrationState *s)
}
qemu_mutex_lock_iothread();
+ /* start block replication */
+ bdrv_start_replication_all(REPLICATION_MODE_PRIMARY, &local_err);
+ if (local_err) {
+ qemu_mutex_unlock_iothread();
+ error_report_err(local_err);
+ ret = -EINVAL;
+ goto out;
+ }
+ trace_colo_start_block_replication();
vm_start();
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("stop", "run");
@@ -506,6 +546,8 @@ static int colo_wait_handle_cmd(QEMUFile *f, int
*checkpoint_request)
case COLO_COMMAND_GUEST_SHUTDOWN:
qemu_mutex_lock_iothread();
vm_stop_force_state(RUN_STATE_COLO);
+ bdrv_stop_replication_all(false, NULL);
+ trace_colo_stop_block_replication("shutdown");
qemu_system_shutdown_request_core();
qemu_mutex_unlock_iothread();
/* the main thread will exit and termiante the whole
@@ -537,6 +579,7 @@ void *colo_process_incoming_thread(void *opaque)
uint64_t total_size;
int ret = 0;
uint64_t value;
+ Error *local_err = NULL;
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_COLO);
@@ -572,6 +615,16 @@ void *colo_process_incoming_thread(void *opaque)
goto out;
}
+ qemu_mutex_lock_iothread();
+ /* start block replication */
+ bdrv_start_replication_all(REPLICATION_MODE_SECONDARY, &local_err);
+ qemu_mutex_unlock_iothread();
+ if (local_err) {
+ error_report_err(local_err);
+ goto out;
+ }
+ trace_colo_start_block_replication();
+
ret = colo_put_cmd(mis->to_src_file, COLO_COMMAND_CHECKPOINT_READY);
if (ret < 0) {
goto out;
@@ -651,6 +704,13 @@ void *colo_process_incoming_thread(void *opaque)
qemu_mutex_unlock_iothread();
goto out;
}
+ /* discard colo disk buffer */
+ bdrv_do_checkpoint_all(&local_err);
+ if (local_err) {
+ vmstate_loading = false;
+ qemu_mutex_unlock_iothread();
+ goto out;
+ }
vmstate_loading = false;
qemu_mutex_unlock_iothread();
diff --git a/trace-events b/trace-events
index 3992b45..3951689 100644
--- a/trace-events
+++ b/trace-events
@@ -1584,6 +1584,8 @@ colo_vm_state_change(const char *old, const char *new)
"Change '%s' => '%s'"
colo_put_cmd(const char *msg) "Send '%s' cmd"
colo_get_cmd(const char *msg) "Receive '%s' cmd"
colo_failover_set_state(int new_state) "new state %d"
+colo_start_block_replication(void) "Block replication is started"
+colo_stop_block_replication(const char *reason) "Block replication is
stopped(reason: '%s')"
# kvm-all.c
kvm_ioctl(int type, void *arg) "type 0x%x, arg %p"
--
1.8.3.1
