[Qemu-devel] [PATCH COLO-Frame v15 38/38] 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>
Cc: Stefan Hajnoczi <address@hidden>
Cc: Kevin Wolf <address@hidden>
Cc: Max Reitz <address@hidden>
---
 migration/colo.c      | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 migration/migration.c |  6 +++++-
 2 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/migration/colo.c b/migration/colo.c
index a2d489b..abb7b14 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -21,6 +21,7 @@
 #include "net/net.h"
 #include "net/filter.h"
 #include "net/vhost_net.h"
+#include "replication.h"
 
 static bool vmstate_loading;
 
@@ -63,6 +64,7 @@ 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.
@@ -80,6 +82,11 @@ 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 */
@@ -170,6 +177,11 @@ static void primary_vm_do_failover(void)
     }
     colo_flush_filter_packets(NULL);
 
+    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_sem);
 }
@@ -329,6 +341,14 @@ 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();
+    replication_do_checkpoint_all(&local_err);
+    qemu_mutex_unlock_iothread();
+    if (local_err) {
+        goto out;
+    }
+
     colo_put_cmd(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
     if (local_err) {
         goto out;
@@ -505,6 +525,13 @@ static void colo_process_checkpoint(MigrationState *s)
     }
 
     qemu_mutex_lock_iothread();
+    /* start block replication */
+    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");
@@ -600,6 +627,7 @@ static void colo_wait_handle_cmd(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();
         /* the main thread will exit and terminate the whole
@@ -669,6 +697,14 @@ void *colo_process_incoming_thread(void *opaque)
         goto out;
     }
 
+    qemu_mutex_lock_iothread();
+    /* start block replication */
+    replication_start_all(REPLICATION_MODE_SECONDARY, &local_err);
+    qemu_mutex_unlock_iothread();
+    if (local_err) {
+        goto out;
+    }
+
     colo_put_cmd(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY,
                  &local_err);
     if (local_err) {
@@ -746,6 +782,18 @@ 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 324dcb6..068edb0 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1591,7 +1591,11 @@ 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 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