[COLO-Frame,v16,35/35] COLO: Add block replication into colo process

Commit Message

Zhanghailiang April 8, 2016, 6:26 a.m. UTC

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

Signed-off-by: zhanghailiang <[e-mail]>
Signed-off-by: Wen Congyang <[e-mail]>
Signed-off-by: Li Zhijian <[e-mail]>
Cc: Stefan Hajnoczi <[e-mail]>
Cc: Kevin Wolf <[e-mail]>
Cc: Max Reitz <[e-mail]>
---
 migration/colo.c      | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 migration/migration.c |  6 +++++-
 2 files changed, 56 insertions(+), 1 deletion(-)

Patch

diff --git a/migration/colo.c b/migration/colo.c
index 6a9caa2..56260d8 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -22,6 +22,8 @@ 
 #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_sem);
 }
@@ -322,6 +335,15 @@  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;
@@ -491,6 +513,13 @@  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");
@@ -586,6 +615,7 @@  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();
         /* the main thread will exit and terminate the whole
@@ -655,6 +685,15 @@  void *colo_process_incoming_thread(void *opaque)
         goto out;
     }
 
+    qemu_mutex_lock_iothread();
+    bdrv_invalidate_cache_all(&local_err);
+    /* start block replication */
+    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) {
@@ -732,6 +771,18 @@  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 58353fe..3bceecc 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1615,7 +1615,11 @@  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) {