[Qemu-devel] [PATCH COLO-Frame (Base) v20 14/17] COLO: Implement the process of failover for primary VM

[zhanghailiang <zhang.zhanghailiang@huawei.com>]

For primary side, if COLO gets failover request from users.
To be exact, gets 'x_colo_lost_heartbeat' command.
COLO thread will exit the loop while the failover BH does the
cleanup work and resumes VM.

Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
v20:
- Remove failover_request_is_active()
v13:
- Add Reviewed-by tag
v12:
- Fix error report and remove unnecessary check in
  primary_vm_do_failover() (Dave's suggestion)
v11:
- Don't call migration_end() in primary_vm_do_failover(),
 The cleanup work will be done in migration_thread().
- Remove vm_start() in primary_vm_do_failover() which also been
  done in migraiton_thread()
v10:
- Call migration_end() in primary_vm_do_failover()
---
 include/migration/colo.h     |  3 +++
 include/migration/failover.h |  1 +
 migration/colo-failover.c    |  2 +-
 migration/colo.c             | 54 ++++++++++++++++++++++++++++++++++++++++++--
 4 files changed, 57 insertions(+), 3 deletions(-)

diff --git a/include/migration/colo.h b/include/migration/colo.h
index e9ac2c3..e32eef4 100644
--- a/include/migration/colo.h
+++ b/include/migration/colo.h
@@ -32,4 +32,7 @@ void *colo_process_incoming_thread(void *opaque);
 bool migration_incoming_in_colo_state(void);
 
 COLOMode get_colo_mode(void);
+
+/* failover */
+void colo_do_failover(MigrationState *s);
 #endif
diff --git a/include/migration/failover.h b/include/migration/failover.h
index 7e0f36a..ad91ef2 100644
--- a/include/migration/failover.h
+++ b/include/migration/failover.h
@@ -21,5 +21,6 @@ FailoverStatus failover_set_state(FailoverStatus old_state,
                                      FailoverStatus new_state);
 FailoverStatus failover_get_state(void);
 void failover_request_active(Error **errp);
+bool failover_request_is_active(void);
 
 #endif
diff --git a/migration/colo-failover.c b/migration/colo-failover.c
index 6cca039..cc229f5 100644
--- a/migration/colo-failover.c
+++ b/migration/colo-failover.c
@@ -36,7 +36,7 @@ static void colo_failover_bh(void *opaque)
         return;
     }
 
-    /* TODO: Do failover work */
+    colo_do_failover(NULL);
 }
 
 void failover_request_active(Error **errp)
diff --git a/migration/colo.c b/migration/colo.c
index b94972c..c1ceed3 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -41,6 +41,40 @@ bool migration_incoming_in_colo_state(void)
     return mis && (mis->state == MIGRATION_STATUS_COLO);
 }
 
+static bool colo_runstate_is_stopped(void)
+{
+    return runstate_check(RUN_STATE_COLO) || !runstate_is_running();
+}
+
+static void primary_vm_do_failover(void)
+{
+    MigrationState *s = migrate_get_current();
+    int old_state;
+
+    migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
+                      MIGRATION_STATUS_COMPLETED);
+
+    old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
+                                   FAILOVER_STATUS_COMPLETED);
+    if (old_state != FAILOVER_STATUS_ACTIVE) {
+        error_report("Incorrect state (%s) while doing failover for Primary VM",
+                     FailoverStatus_lookup[old_state]);
+        return;
+    }
+}
+
+void colo_do_failover(MigrationState *s)
+{
+    /* Make sure VM stopped while failover happened. */
+    if (!colo_runstate_is_stopped()) {
+        vm_stop_force_state(RUN_STATE_COLO);
+    }
+
+    if (get_colo_mode() == COLO_MODE_PRIMARY) {
+        primary_vm_do_failover();
+    }
+}
+
 static void colo_send_message(QEMUFile *f, COLOMessage msg,
                               Error **errp)
 {
@@ -162,9 +196,20 @@ static int colo_do_checkpoint_transaction(MigrationState *s,
     bioc->usage = 0;
 
     qemu_mutex_lock_iothread();
+    if (failover_get_state() != FAILOVER_STATUS_NONE) {
+        qemu_mutex_unlock_iothread();
+        goto out;
+    }
     vm_stop_force_state(RUN_STATE_COLO);
     qemu_mutex_unlock_iothread();
     trace_colo_vm_state_change("run", "stop");
+    /*
+     * Failover request bh could be called after vm_stop_force_state(),
+     * So we need check failover_request_is_active() again.
+     */
+    if (failover_get_state() != FAILOVER_STATUS_NONE) {
+        goto out;
+    }
 
     /* Disable block migration */
     s->params.blk = 0;
@@ -259,6 +304,11 @@ static void colo_process_checkpoint(MigrationState *s)
     trace_colo_vm_state_change("stop", "run");
 
     while (s->state == MIGRATION_STATUS_COLO) {
+        if (failover_get_state() != FAILOVER_STATUS_NONE) {
+            error_report("failover request");
+            goto out;
+        }
+
         current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
         if (current_time - checkpoint_time <
             s->parameters.x_checkpoint_delay) {
@@ -280,9 +330,9 @@ out:
     if (local_err) {
         error_report_err(local_err);
     }
-    migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
-                      MIGRATION_STATUS_COMPLETED);
+
     qemu_fclose(fb);
+
     if (s->rp_state.from_dst_file) {
         qemu_fclose(s->rp_state.from_dst_file);
     }
-- 
1.8.3.1