COLO: Add 'x-colo-lost-heartbeat' command to trigger failover

We leave users to choose whatever heartbeat solution they want,
if the heartbeat is lost, or other errors they detect, they can use
experimental command 'x_colo_lost_heartbeat' to tell COLO to do failover,
COLO will do operations accordingly.

For example, if the command is sent to the Primary side,
the Primary side will exit COLO mode, does cleanup work,
and then, PVM will take over the service work. If sent to the Secondary side,
the Secondary side will run failover work, then takes over PVM's service work.

Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Eric Blake <eblake@redhat.com>
Cc: Markus Armbruster <armbru@redhat.com>
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>
Reviewed-by: Amit Shah <amit.shah@redhat.com>
Signed-off-by: Amit Shah <amit@amitshah.net>

docs/qmp-commands.txt

@@ -554,6 +554,16 @@ Example:
 -> { "execute": "migrate_set_downtime", "arguments": { "value": 0.1 } }
 <- { "return": {} }
 
+x-colo-lost-heartbeat
+--------------------
+
+Tell COLO that heartbeat is lost, a failover or takeover is needed.
+
+Example:
+
+-> { "execute": "x-colo-lost-heartbeat" }
+<- { "return": {} }
+
 client_migrate_info
 -------------------
 

hmp-commands.hx

@@ -1037,6 +1037,21 @@ STEXI
 @findex migrate_start_postcopy
 Switch in-progress migration to postcopy mode. Ignored after the end of
 migration (or once already in postcopy).
+ETEXI
+
+    {
+        .name       = "x_colo_lost_heartbeat",
+        .args_type  = "",
+        .params     = "",
+        .help       = "Tell COLO that heartbeat is lost,\n\t\t\t"
+                      "a failover or takeover is needed.",
+        .cmd = hmp_x_colo_lost_heartbeat,
+    },
+
+STEXI
+@item x_colo_lost_heartbeat
+@findex x_colo_lost_heartbeat
+Tell COLO that heartbeat is lost, a failover or takeover is needed.
 ETEXI
 
     {

hmp.c

@@ -1451,6 +1451,14 @@ void hmp_migrate_start_postcopy(Monitor *mon, const QDict *qdict)
     hmp_handle_error(mon, &err);
 }
 
+void hmp_x_colo_lost_heartbeat(Monitor *mon, const QDict *qdict)
+{
+    Error *err = NULL;
+
+    qmp_x_colo_lost_heartbeat(&err);
+    hmp_handle_error(mon, &err);
+}
+
 void hmp_set_password(Monitor *mon, const QDict *qdict)
 {
     const char *protocol  = qdict_get_str(qdict, "protocol");

hmp.h

@@ -72,6 +72,7 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict);
 void hmp_migrate_set_cache_size(Monitor *mon, const QDict *qdict);
 void hmp_client_migrate_info(Monitor *mon, const QDict *qdict);
 void hmp_migrate_start_postcopy(Monitor *mon, const QDict *qdict);
+void hmp_x_colo_lost_heartbeat(Monitor *mon, const QDict *qdict);
 void hmp_set_password(Monitor *mon, const QDict *qdict);
 void hmp_expire_password(Monitor *mon, const QDict *qdict);
 void hmp_eject(Monitor *mon, const QDict *qdict);

include/migration/colo.h

@@ -17,6 +17,7 @@
 #include "migration/migration.h"
 #include "qemu/coroutine_int.h"
 #include "qemu/thread.h"
+#include "qemu/main-loop.h"
 
 bool colo_supported(void);
 void colo_info_init(void);
@@ -29,4 +30,6 @@ bool migration_incoming_enable_colo(void);
 void migration_incoming_exit_colo(void);
 void *colo_process_incoming_thread(void *opaque);
 bool migration_incoming_in_colo_state(void);
+
+COLOMode get_colo_mode(void);
 #endif

include/migration/failover.h

@@ -0,0 +1,20 @@
+/*
+ *  COarse-grain LOck-stepping Virtual Machines for Non-stop Service (COLO)
+ *  (a.k.a. Fault Tolerance or Continuous Replication)
+ *
+ * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO.,LTD.
+ * Copyright (c) 2016 FUJITSU LIMITED
+ * Copyright (c) 2016 Intel Corporation
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * later.  See the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_FAILOVER_H
+#define QEMU_FAILOVER_H
+
+#include "qemu-common.h"
+
+void failover_request_active(Error **errp);
+
+#endif

migration/Makefile.objs

@@ -1,7 +1,7 @@
 common-obj-y += migration.o socket.o fd.o exec.o
 common-obj-y += tls.o
-common-obj-$(CONFIG_COLO) += colo.o
 common-obj-y += colo-comm.o
+common-obj-$(CONFIG_COLO) += colo.o colo-failover.o
 common-obj-y += vmstate.o
 common-obj-y += qemu-file.o
 common-obj-y += qemu-file-channel.o

migration/colo-comm.c

@@ -21,6 +21,17 @@ typedef struct {
 
 static COLOInfo colo_info;
 
+COLOMode get_colo_mode(void)
+{
+    if (migration_in_colo_state()) {
+        return COLO_MODE_PRIMARY;
+    } else if (migration_incoming_in_colo_state()) {
+        return COLO_MODE_SECONDARY;
+    } else {
+        return COLO_MODE_UNKNOWN;
+    }
+}
+
 static void colo_info_pre_save(void *opaque)
 {
     COLOInfo *s = opaque;

migration/colo-failover.c

@@ -0,0 +1,42 @@
+/*
+ * COarse-grain LOck-stepping Virtual Machines for Non-stop Service (COLO)
+ * (a.k.a. Fault Tolerance or Continuous Replication)
+ *
+ * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO., LTD.
+ * Copyright (c) 2016 FUJITSU LIMITED
+ * Copyright (c) 2016 Intel Corporation
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * later.  See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "migration/colo.h"
+#include "migration/failover.h"
+#include "qmp-commands.h"
+#include "qapi/qmp/qerror.h"
+
+static QEMUBH *failover_bh;
+
+static void colo_failover_bh(void *opaque)
+{
+    qemu_bh_delete(failover_bh);
+    failover_bh = NULL;
+    /* TODO: Do failover work */
+}
+
+void failover_request_active(Error **errp)
+{
+    failover_bh = qemu_bh_new(colo_failover_bh, NULL);
+    qemu_bh_schedule(failover_bh);
+}
+
+void qmp_x_colo_lost_heartbeat(Error **errp)
+{
+    if (get_colo_mode() == COLO_MODE_UNKNOWN) {
+        error_setg(errp, QERR_FEATURE_DISABLED, "colo");
+        return;
+    }
+
+    failover_request_active(errp);
+}

migration/colo.c

@@ -18,6 +18,7 @@
 #include "trace.h"
 #include "qemu/error-report.h"
 #include "qapi/error.h"
+#include "migration/failover.h"
 
 #define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024)
 

qapi-schema.json

@@ -823,6 +823,35 @@
             'vmstate-send', 'vmstate-size', 'vmstate-received',
             'vmstate-loaded' ] }
 
+##
+# @COLOMode
+#
+# The colo mode
+#
+# @unknown: unknown mode
+#
+# @primary: master side
+#
+# @secondary: slave side
+#
+# Since: 2.8
+##
+{ 'enum': 'COLOMode',
+  'data': [ 'unknown', 'primary', 'secondary'] }
+
+##
+# @x-colo-lost-heartbeat
+#
+# Tell qemu that heartbeat is lost, request it to do takeover procedures.
+# If this command is sent to the PVM, the Primary side will exit COLO mode.
+# If sent to the Secondary, the Secondary side will run failover work,
+# then takes over server operation to become the service VM.
+#
+# Since: 2.8
+##
+{ 'command': 'x-colo-lost-heartbeat' }
+
+##
 # @MouseInfo:
 #
 # Information about a mouse device.

stubs/migration-colo.c

@@ -12,6 +12,7 @@
 
 #include "qemu/osdep.h"
 #include "migration/colo.h"
+#include "qmp-commands.h"
 
 bool colo_supported(void)
 {
@@ -36,3 +37,10 @@ void *colo_process_incoming_thread(void *opaque)
 {
     return NULL;
 }
+
+void qmp_x_colo_lost_heartbeat(Error **errp)
+{
+    error_setg(errp, "COLO is not supported, please rerun configure"
+                     " with --enable-colo option in order to support"
+                     " COLO feature");
+}