[Qemu-devel] [PATCH COLO-Frame v14 04/40] migration: Integrate COLO checkpoint process into migration

[zhanghailiang]

Add a migrate state: MIGRATION_STATUS_COLO, enter this migration state
after the first live migration successfully finished.

We reuse migration thread, so if colo is enabled by user, migration thread will
go into the process of colo.

Signed-off-by: zhanghailiang <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
Signed-off-by: Gonglei <address@hidden>
Reviewed-by: Dr. David Alan Gilbert <address@hidden>
---
v11:
- Rebase to master
- Add Reviewed-by tag
v10:
- Simplify process by dropping colo thread and reusing migration thread.
     (Dave's suggestion)
---
 include/migration/colo.h |  3 +++
 migration/colo.c         | 31 +++++++++++++++++++++++++++++++
 migration/migration.c    | 30 ++++++++++++++++++++++++++----
 qapi-schema.json         |  4 +++-
 stubs/migration-colo.c   |  9 +++++++++
 trace-events             |  3 +++
 6 files changed, 75 insertions(+), 5 deletions(-)

diff --git a/include/migration/colo.h b/include/migration/colo.h
index 1c899a0..bf84b99 100644
--- a/include/migration/colo.h
+++ b/include/migration/colo.h
@@ -19,4 +19,7 @@
 bool colo_supported(void);
 void colo_info_init(void);
 
+void migrate_start_colo_process(MigrationState *s);
+bool migration_in_colo_state(void);
+
 #endif
diff --git a/migration/colo.c b/migration/colo.c
index cb3e22d..8d0d851 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -10,9 +10,40 @@
  * later.  See the COPYING file in the top-level directory.
  */
 
+#include "sysemu/sysemu.h"
 #include "migration/colo.h"
+#include "trace.h"
 
 bool colo_supported(void)
 {
     return true;
 }
+
+bool migration_in_colo_state(void)
+{
+    MigrationState *s = migrate_get_current();
+
+    return (s->state == MIGRATION_STATUS_COLO);
+}
+
+static void colo_process_checkpoint(MigrationState *s)
+{
+    qemu_mutex_lock_iothread();
+    vm_start();
+    qemu_mutex_unlock_iothread();
+    trace_colo_vm_state_change("stop", "run");
+
+    /*TODO: COLO checkpoint savevm loop*/
+
+    migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
+                      MIGRATION_STATUS_COMPLETED);
+}
+
+void migrate_start_colo_process(MigrationState *s)
+{
+    qemu_mutex_unlock_iothread();
+    migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
+                      MIGRATION_STATUS_COLO);
+    colo_process_checkpoint(s);
+    qemu_mutex_lock_iothread();
+}
diff --git a/migration/migration.c b/migration/migration.c
index 7de6a99..df739b5 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -641,6 +641,10 @@ MigrationInfo *qmp_query_migrate(Error **errp)
 
         get_xbzrle_cache_stats(info);
         break;
+    case MIGRATION_STATUS_COLO:
+        info->has_status = true;
+        /* TODO: display COLO specific information (checkpoint info etc.) */
+        break;
     case MIGRATION_STATUS_COMPLETED:
         get_xbzrle_cache_stats(info);
 
@@ -1001,7 +1005,8 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk,
     params.shared = has_inc && inc;
 
     if (migration_is_setup_or_active(s->state) ||
-        s->state == MIGRATION_STATUS_CANCELLING) {
+        s->state == MIGRATION_STATUS_CANCELLING ||
+        s->state == MIGRATION_STATUS_COLO) {
         error_setg(errp, QERR_MIGRATION_ACTIVE);
         return;
     }
@@ -1601,8 +1606,11 @@ static void migration_completion(MigrationState *s, int 
current_active_state,
         goto fail;
     }
 
-    migrate_set_state(&s->state, current_active_state,
-                      MIGRATION_STATUS_COMPLETED);
+    if (!migrate_colo_enabled()) {
+        migrate_set_state(&s->state, current_active_state,
+                          MIGRATION_STATUS_COMPLETED);
+    }
+
     return;
 
 fail:
@@ -1634,6 +1642,7 @@ static void *migration_thread(void *opaque)
     bool entered_postcopy = false;
     /* The active state we expect to be in; ACTIVE or POSTCOPY_ACTIVE */
     enum MigrationStatus current_active_state = MIGRATION_STATUS_ACTIVE;
+    bool enable_colo = migrate_colo_enabled();
 
     rcu_register_thread();
 
@@ -1742,7 +1751,11 @@ static void *migration_thread(void *opaque)
     end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
 
     qemu_mutex_lock_iothread();
-    qemu_savevm_state_cleanup();
+    /* The resource has been allocated by migration will be reused in COLO
+      process, so don't release them. */
+    if (!enable_colo) {
+        qemu_savevm_state_cleanup();
+    }
     if (s->state == MIGRATION_STATUS_COMPLETED) {
         uint64_t transferred_bytes = qemu_ftell(s->to_dst_file);
         s->total_time = end_time - s->total_time;
@@ -1755,6 +1768,15 @@ static void *migration_thread(void *opaque)
         }
         runstate_set(RUN_STATE_POSTMIGRATE);
     } else {
+        if (s->state == MIGRATION_STATUS_ACTIVE && enable_colo) {
+            migrate_start_colo_process(s);
+            qemu_savevm_state_cleanup();
+            /*
+            * Fixme: we will run VM in COLO no matter its old running state.
+            * After exited COLO, we will keep running.
+            */
+            old_vm_running = true;
+        }
         if (old_vm_running && !entered_postcopy) {
             vm_start();
         }
diff --git a/qapi-schema.json b/qapi-schema.json
index aafa9f7..26a1d37 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -434,12 +434,14 @@
 #
 # @failed: some error occurred during migration process.
 #
+# @colo: VM is in the process of fault tolerance. (since 2.6)
+#
 # Since: 2.3
 #
 ##
 { 'enum': 'MigrationStatus',
   'data': [ 'none', 'setup', 'cancelling', 'cancelled',
-            'active', 'postcopy-active', 'completed', 'failed' ] }
+            'active', 'postcopy-active', 'completed', 'failed', 'colo' ] }
 
 ##
 # @MigrationInfo
diff --git a/stubs/migration-colo.c b/stubs/migration-colo.c
index 7b7aee0..41fed49 100644
--- a/stubs/migration-colo.c
+++ b/stubs/migration-colo.c
@@ -16,3 +16,12 @@ bool colo_supported(void)
 {
     return false;
 }
+
+bool migration_in_colo_state(void)
+{
+    return false;
+}
+
+void migrate_start_colo_process(MigrationState *s)
+{
+}
diff --git a/trace-events b/trace-events
index c9ac144..1c3bc8e 100644
--- a/trace-events
+++ b/trace-events
@@ -1581,6 +1581,9 @@ postcopy_ram_incoming_cleanup_entry(void) ""
 postcopy_ram_incoming_cleanup_exit(void) ""
 postcopy_ram_incoming_cleanup_join(void) ""
 
+# migration/colo.c
+colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'"
+
 # kvm-all.c
 kvm_ioctl(int type, void *arg) "type 0x%x, arg %p"
 kvm_vm_ioctl(int type, void *arg) "type 0x%x, arg %p"
-- 
1.8.3.1