[Qemu-devel] [PATCH COLO-Frame v11 21/39] COLO failover: Introduce a new command to trigger a failover

[zhanghailiang]

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 PVM, the Primary side will
exit COLO mode and take over operation. If sent to the Secondary, the
secondary will run failover work, then take over server operation to
become the new Primary.

Cc: Luiz Capitulino <address@hidden>
Cc: Eric Blake <address@hidden>
Cc: Markus Armbruster <address@hidden>
Signed-off-by: zhanghailiang <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
---
v11:
- Add more comments for x-colo-lost-heartbeat command (Eric's suggestion)
- Return 'enum' instead of 'int' for get_colo_mode() (Eric's suggestion)
v10:
- Rename command colo_lost_hearbeat to experimental 'x_colo_lost_heartbeat'
---
 hmp-commands.hx              | 15 +++++++++++++++
 hmp.c                        |  8 ++++++++
 hmp.h                        |  1 +
 include/migration/colo.h     |  3 +++
 include/migration/failover.h | 20 ++++++++++++++++++++
 migration/Makefile.objs      |  2 +-
 migration/colo-comm.c        | 11 +++++++++++
 migration/colo-failover.c    | 41 +++++++++++++++++++++++++++++++++++++++++
 migration/colo.c             |  1 +
 qapi-schema.json             | 29 +++++++++++++++++++++++++++++
 qmp-commands.hx              | 19 +++++++++++++++++++
 stubs/migration-colo.c       |  8 ++++++++
 12 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 include/migration/failover.h
 create mode 100644 migration/colo-failover.c

diff --git a/hmp-commands.hx b/hmp-commands.hx
index bb52e4d..a381b0b 100644
--- a/hmp-commands.hx
+++ b/hmp-commands.hx
@@ -1039,6 +1039,21 @@ 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.",
+        .mhandler.cmd = hmp_x_colo_lost_heartbeat,
+    },
+
+STEXI
address@hidden x_colo_lost_heartbeat
address@hidden x_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 ec038f1..ce8a23c 100644
--- a/hmp.c
+++ b/hmp.c
@@ -1310,6 +1310,14 @@ 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");
diff --git a/hmp.h b/hmp.h
index a8c5b5a..864a300 100644
--- a/hmp.h
+++ b/hmp.h
@@ -70,6 +70,7 @@ 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);
diff --git a/include/migration/colo.h b/include/migration/colo.h
index 2676c4a..ba27719 100644
--- a/include/migration/colo.h
+++ b/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_mig_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
diff --git a/include/migration/failover.h b/include/migration/failover.h
new file mode 100644
index 0000000..1785b52
--- /dev/null
+++ b/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) 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 QEMU_FAILOVER_H
+#define QEMU_FAILOVER_H
+
+#include "qemu-common.h"
+
+void failover_request_active(Error **errp);
+
+#endif
diff --git a/migration/Makefile.objs b/migration/Makefile.objs
index 81b5713..920d1e7 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 postcopy-ram.o
diff --git a/migration/colo-comm.c b/migration/colo-comm.c
index 30df3d3..58a6488 100644
--- a/migration/colo-comm.c
+++ b/migration/colo-comm.c
@@ -20,6 +20,17 @@ 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;
diff --git a/migration/colo-failover.c b/migration/colo-failover.c
new file mode 100644
index 0000000..e3897c6
--- /dev/null
+++ b/migration/colo-failover.c
@@ -0,0 +1,41 @@
+/*
+ * 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/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);
+}
diff --git a/migration/colo.c b/migration/colo.c
index 5b7ff87..2c4fc1c 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -17,6 +17,7 @@
 #include "trace.h"
 #include "qemu/error-report.h"
 #include "qemu/sockets.h"
+#include "migration/failover.h"
 
 /* colo buffer */
 #define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024)
diff --git a/qapi-schema.json b/qapi-schema.json
index b4b47ed..2ed63e0 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -765,6 +765,35 @@
             'checkpoint-reply', 'vmstate-send', 'vmstate-size',
             'vmstate-received', 'vmstate-loaded' ] }
 
+##
+# @COLOMode
+#
+# The colo mode
+#
+# @unknown: unknown mode
+#
+# @primary: master side
+#
+# @secondary: slave side
+#
+# Since: 2.6
+##
+{ '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: 2.6
+##
+{ 'command': 'x-colo-lost-heartbeat' }
+
+##
 # @MouseInfo:
 #
 # Information about a mouse device.
diff --git a/qmp-commands.hx b/qmp-commands.hx
index c39f2f0..6e79511 100644
--- a/qmp-commands.hx
+++ b/qmp-commands.hx
@@ -805,6 +805,25 @@ Example:
 EQMP
 
     {
+        .name       = "x-colo-lost-heartbeat",
+        .args_type  = "",
+        .mhandler.cmd_new = qmp_marshal_x_colo_lost_heartbeat,
+    },
+
+SQMP
+x-colo-lost-heartbeat
+--------------------
+
+Tell COLO that heartbeat is lost, a failover or takeover is needed.
+
+Example:
+
+-> { "execute": "x-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 c12516e..5028f63 100644
--- a/stubs/migration-colo.c
+++ b/stubs/migration-colo.c
@@ -11,6 +11,7 @@
  */
 
 #include "migration/colo.h"
+#include "qmp-commands.h"
 
 bool colo_supported(void)
 {
@@ -35,3 +36,10 @@ 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");
+}
-- 
1.8.3.1