[Qemu-devel] [PATCH COLO-Frame v8 32/34] COLO NIC: Implement NIC checkpoint and failover

[zhanghailiang]

Signed-off-by: zhanghailiang <zhang.zhanghaili...@huawei.com>
Signed-off-by: Li Zhijian <lizhij...@cn.fujitsu.com>
---
 include/net/colo-nic.h |  2 ++
 migration/colo.c       | 22 +++++++++++++++++++---
 net/colo-nic.c         | 23 +++++++++++++++++++++++
 3 files changed, 44 insertions(+), 3 deletions(-)

diff --git a/include/net/colo-nic.h b/include/net/colo-nic.h
index 271ab8b..a9960f1 100644
--- a/include/net/colo-nic.h
+++ b/include/net/colo-nic.h
@@ -31,5 +31,7 @@ int colo_proxy_init(enum COLOMode mode);
 void colo_proxy_destroy(enum COLOMode mode);
 
 int colo_proxy_compare(void);
+int colo_proxy_failover(void);
+int colo_proxy_checkpoint(enum COLOMode mode);
 
 #endif
diff --git a/migration/colo.c b/migration/colo.c
index b466959..2b518d4 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -148,6 +148,12 @@ static void secondary_vm_do_failover(void)
 
     migrate_set_state(&mis->state, MIGRATION_STATUS_COLO,
                       MIGRATION_STATUS_COMPLETED);
+
+    if (colo_proxy_failover() != 0) {
+        error_report("colo proxy failed to do failover");
+    }
+    colo_proxy_destroy(COLO_MODE_SECONDARY);
+
     if (!autostart) {
         error_report("\"-S\" qemu option will be ignored in secondary side");
         /* recover runstate to normal migration finish state */
@@ -177,6 +183,8 @@ static void primary_vm_do_failover(void)
     MigrationState *s = migrate_get_current();
     int old_state;
 
+    colo_proxy_destroy(COLO_MODE_PRIMARY);
+
     if (s->state != MIGRATION_STATUS_FAILED) {
         migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
                           MIGRATION_STATUS_COMPLETED);
@@ -318,6 +326,11 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s, QEMUFile *control)
 
     qemu_fflush(trans);
 
+    ret = colo_proxy_checkpoint(COLO_MODE_PRIMARY);
+    if (ret < 0) {
+        goto out;
+    }
+
     ret = colo_ctl_put(s->file, COLO_CHECKPOINT_SEND);
     if (ret < 0) {
         goto out;
@@ -463,8 +476,6 @@ out:
     }
     qemu_mutex_unlock_iothread();
 
-    colo_proxy_destroy(COLO_MODE_PRIMARY);
-
     return NULL;
 }
 
@@ -592,6 +603,11 @@ void *colo_process_incoming_checkpoints(void *opaque)
             goto out;
         }
 
+        ret = colo_proxy_checkpoint(COLO_MODE_SECONDARY);
+        if (ret < 0) {
+            goto out;
+        }
+
         ret = colo_ctl_get(f, COLO_CHECKPOINT_SEND);
         if (ret < 0) {
             goto out;
@@ -688,10 +704,10 @@ out:
         * just kill Secondary VM
         */
         error_report("SVM is going to exit in default!");
+        colo_proxy_destroy(COLO_MODE_SECONDARY);
         exit(1);
     }
 
-    colo_proxy_destroy(COLO_MODE_SECONDARY);
     migration_incoming_exit_colo();
 
     return NULL;
diff --git a/net/colo-nic.c b/net/colo-nic.c
index d2073b8..62bd35a 100644
--- a/net/colo-nic.c
+++ b/net/colo-nic.c
@@ -428,6 +428,29 @@ void colo_proxy_destroy(enum COLOMode mode)
     teardown_nic(mode, getpid());
 }
 
+/*
+* Note: Weird, Only the VM in slave side need to do failover work !!!
+*/
+int colo_proxy_failover(void)
+{
+    if (colo_proxy_send(NFCOLO_DO_FAILOVER, COLO_MODE_SECONDARY, 0, NULL) < 0) 
{
+        return -1;
+    }
+
+    return 0;
+}
+
+/*
+* Note: Only the VM in master side need to do checkpoint
+*/
+int colo_proxy_checkpoint(enum COLOMode  mode)
+{
+    if (colo_proxy_send(NFCOLO_DO_CHECKPOINT, mode, 0, NULL) < 0) {
+        return -1;
+    }
+    return 0;
+}
+
 int colo_proxy_compare(void)
 {
     return atomic_xchg(&packet_compare_different, 0);
-- 
1.8.3.1