[Qemu-devel] [PATCH COLO-Frame v13 39/39] COLO: Add block replication into colo process

[zhanghailiang]

Make sure master start block replication after slave's block replication 
started.

Signed-off-by: zhanghailiang <address@hidden>
Signed-off-by: Wen Congyang <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
---
 migration/colo.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 trace-events     |  2 ++
 2 files changed, 54 insertions(+)

diff --git a/migration/colo.c b/migration/colo.c
index 23e1131..c08a3ff 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -20,6 +20,7 @@
 #include "qapi-event.h"
 #include "net/filter.h"
 #include "net/net.h"
+#include "block/block_int.h"
 
 static bool vmstate_loading;
 
@@ -54,6 +55,7 @@ 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.
@@ -71,6 +73,12 @@ 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 */
@@ -108,6 +116,7 @@ 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);
@@ -136,6 +145,12 @@ static void primary_vm_do_failover(void)
     /* 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");
+
     /* Notify COLO thread that failover work is finished */
     qemu_sem_post(&s->colo_sem);
 }
@@ -297,6 +312,14 @@ 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) {
+        goto out;
+    }
+
     colo_put_cmd(s->to_dst_file, COLO_COMMAND_VMSTATE_SEND, &local_err);
     if (local_err) {
         goto out;
@@ -345,6 +368,10 @@ 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, &local_err);
         if (local_err) {
             goto out;
@@ -439,6 +466,13 @@ 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();
+        goto out;
+    }
+    trace_colo_start_block_replication();
     vm_start();
     qemu_mutex_unlock_iothread();
     trace_colo_vm_state_change("stop", "run");
@@ -534,6 +568,8 @@ static void 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 terminate the whole
@@ -603,6 +639,15 @@ 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) {
+        goto out;
+    }
+    trace_colo_start_block_replication();
+
     colo_put_cmd(mis->to_src_file, COLO_COMMAND_CHECKPOINT_READY,
                  &local_err);
     if (local_err) {
@@ -680,6 +725,13 @@ 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 a50bf45..e04acde 100644
--- a/trace-events
+++ b/trace-events
@@ -1586,6 +1586,8 @@ 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