[Qemu-devel] [RFC PATCH v4 14/28] COLO failover: Introduce a new command to trigger a failover

[zhanghailiang]

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

For example,
If send the command to PVM, Primary will exit COLO mode, and takeover,
if to Secondary, Secondary will do failover work and at last takeover server.

Signed-off-by: zhanghailiang <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
Signed-off-by: Lai Jiangshan <address@hidden>
Signed-off-by: Yang Hongyang <address@hidden>
---
 hmp-commands.hx                        | 15 ++++++++++++++
 hmp.c                                  |  7 +++++++
 hmp.h                                  |  1 +
 include/migration/migration-colo.h     |  1 +
 include/migration/migration-failover.h | 20 ++++++++++++++++++
 migration/Makefile.objs                |  2 +-
 migration/colo-failover.c              | 38 ++++++++++++++++++++++++++++++++++
 migration/colo.c                       |  1 +
 qapi-schema.json                       |  9 ++++++++
 qmp-commands.hx                        | 19 +++++++++++++++++
 stubs/migration-colo.c                 |  8 +++++++
 11 files changed, 120 insertions(+), 1 deletion(-)
 create mode 100644 include/migration/migration-failover.h
 create mode 100644 migration/colo-failover.c

diff --git a/hmp-commands.hx b/hmp-commands.hx
index 3089533..e615889 100644
--- a/hmp-commands.hx
+++ b/hmp-commands.hx
@@ -993,6 +993,21 @@ Enable/Disable the usage of a capability @var{capability} 
for migration.
 ETEXI
 
     {
+        .name       = "colo_lost_heartbeat",
+        .args_type  = "",
+        .params     = "",
+        .help       = "Tell COLO that heartbeat is lost,\n\t\t\t"
+                      "a failover or takeover is needed.",
+        .mhandler.cmd = hmp_colo_lost_heartbeat,
+    },
+
+STEXI
address@hidden colo_lost_heartbeat
address@hidden colo_lost_heartbeat
+Tell COLO that heartbeat is lost, a failover or takeover is needed.
+ETEXI
+
+    {
         .name       = "client_migrate_info",
         .args_type  = 
"protocol:s,hostname:s,port:i?,tls-port:i?,cert-subject:s?",
         .params     = "protocol hostname port tls-port cert-subject",
diff --git a/hmp.c b/hmp.c
index f31ae27..ee0e139 100644
--- a/hmp.c
+++ b/hmp.c
@@ -1184,6 +1184,13 @@ void hmp_migrate_set_capability(Monitor *mon, const 
QDict *qdict)
     }
 }
 
+void hmp_colo_lost_heartbeat(Monitor *mon, const QDict *qdict)
+{
+    Error *err = NULL;
+    qmp_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");
diff --git a/hmp.h b/hmp.h
index 2b9308b..af85144 100644
--- a/hmp.h
+++ b/hmp.h
@@ -65,6 +65,7 @@ void hmp_migrate_set_downtime(Monitor *mon, const QDict 
*qdict);
 void hmp_migrate_set_speed(Monitor *mon, const QDict *qdict);
 void hmp_migrate_set_capability(Monitor *mon, const QDict *qdict);
 void hmp_migrate_set_cache_size(Monitor *mon, const QDict *qdict);
+void hmp_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);
diff --git a/include/migration/migration-colo.h 
b/include/migration/migration-colo.h
index 7e177f8..593431a 100644
--- a/include/migration/migration-colo.h
+++ b/include/migration/migration-colo.h
@@ -17,6 +17,7 @@
 #include "migration/migration.h"
 #include "block/coroutine.h"
 #include "qemu/thread.h"
+#include "qemu/main-loop.h"
 
 bool colo_supported(void);
 void colo_info_mig_init(void);
diff --git a/include/migration/migration-failover.h 
b/include/migration/migration-failover.h
new file mode 100644
index 0000000..a8767fc
--- /dev/null
+++ b/include/migration/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) 2015 HUAWEI TECHNOLOGIES CO.,LTD.
+ * Copyright (c) 2015 FUJITSU LIMITED
+ * Copyright (c) 2015 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 MIGRATION_FAILOVER_H
+#define MIGRATION_FAILOVER_H
+
+#include "qemu-common.h"
+
+void failover_request_set(void);
+
+#endif
diff --git a/migration/Makefile.objs b/migration/Makefile.objs
index cb7bd30..50d8392 100644
--- a/migration/Makefile.objs
+++ b/migration/Makefile.objs
@@ -1,6 +1,6 @@
 common-obj-y += migration.o tcp.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 qemu-file-buf.o qemu-file-unix.o qemu-file-stdio.o
 common-obj-y += xbzrle.o
diff --git a/migration/colo-failover.c b/migration/colo-failover.c
new file mode 100644
index 0000000..af78054
--- /dev/null
+++ b/migration/colo-failover.c
@@ -0,0 +1,38 @@
+/*
+ * COarse-grain LOck-stepping Virtual Machines for Non-stop Service (COLO)
+ * (a.k.a. Fault Tolerance or Continuous Replication)
+ *
+ * Copyright (c) 2015 HUAWEI TECHNOLOGIES CO.,LTD.
+ * Copyright (c) 2015 FUJITSU LIMITED
+ * Copyright (c) 2015 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 "migration/migration-colo.h"
+#include "migration/migration-failover.h"
+#include "qmp-commands.h"
+
+static bool failover_request;
+
+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_set(void)
+{
+    failover_request = true;
+    failover_bh = qemu_bh_new(colo_failover_bh, NULL);
+    qemu_bh_schedule(failover_bh);
+}
+
+void qmp_colo_lost_heartbeat(Error **errp)
+{
+    failover_request_set();
+}
diff --git a/migration/colo.c b/migration/colo.c
index 386f5f5..ce41afb 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -13,6 +13,7 @@
 #include "sysemu/sysemu.h"
 #include "migration/migration-colo.h"
 #include "qemu/error-report.h"
+#include "migration/migration-failover.h"
 
 #define DEBUG_COLO 0
 
diff --git a/qapi-schema.json b/qapi-schema.json
index 43a964b..e11c152 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -567,6 +567,15 @@
 { 'command': 'query-migrate-capabilities', 'returns':   
['MigrationCapabilityStatus']}
 
 ##
+# @colo-lost-heartbeat
+#
+# Tell COLO that heartbeat is lost
+#
+# Since: 2.4
+##
+{ 'command': 'colo-lost-heartbeat' }
+
+##
 # @MouseInfo:
 #
 # Information about a mouse device.
diff --git a/qmp-commands.hx b/qmp-commands.hx
index 7f68760..85d3d72 100644
--- a/qmp-commands.hx
+++ b/qmp-commands.hx
@@ -781,6 +781,25 @@ Example:
 EQMP
 
     {
+        .name       = "colo-lost-heartbeat",
+        .args_type  = "",
+        .mhandler.cmd_new = qmp_marshal_input_colo_lost_heartbeat,
+    },
+
+SQMP
+colo-lost-heartbeat
+--------------------
+
+Tell COLO that heartbeat is lost, a failover or takeover is needed.
+
+Example:
+
+-> { "execute": "colo-lost-heartbeat" }
+<- { "return": {} }
+
+EQMP
+
+    {
         .name       = "client_migrate_info",
         .args_type  = 
"protocol:s,hostname:s,port:i?,tls-port:i?,cert-subject:s?",
         .params     = "protocol hostname port tls-port cert-subject",
diff --git a/stubs/migration-colo.c b/stubs/migration-colo.c
index cbadcd6..82fe14c 100644
--- a/stubs/migration-colo.c
+++ b/stubs/migration-colo.c
@@ -11,6 +11,7 @@
  */
 
 #include "migration/migration-colo.h"
+#include "qmp-commands.h"
 
 bool colo_supported(void)
 {
@@ -30,3 +31,10 @@ void *colo_process_incoming_checkpoints(void *opaque)
 {
     return NULL;
 }
+
+void qmp_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");
+}
-- 
1.7.12.4