[Qemu-devel] [PATCH COLO-Frame v11 26/39] qmp event: Add event notification for COLO error

[zhanghailiang]

If some errors happen during VM's COLO FT stage, it's important to notify the 
users
of this event. Together with 'colo_lost_heartbeat', users can intervene in 
COLO's
failover work immediately.
If users don't want to get involved in COLO's failover verdict,
it is still necessary to notify users that we exited COLO mode.

Cc: Markus Armbruster <address@hidden>
Cc: Michael Roth <address@hidden>
Signed-off-by: zhanghailiang <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
---
v11:
- Fix several typos found by Eric
---
 docs/qmp-events.txt | 17 +++++++++++++++++
 migration/colo.c    | 13 +++++++++++++
 qapi-schema.json    | 16 ++++++++++++++++
 qapi/event.json     | 17 +++++++++++++++++
 4 files changed, 63 insertions(+)

diff --git a/docs/qmp-events.txt b/docs/qmp-events.txt
index d2f1ce4..19f68fc 100644
--- a/docs/qmp-events.txt
+++ b/docs/qmp-events.txt
@@ -184,6 +184,23 @@ Example:
 Note: The "ready to complete" status is always reset by a BLOCK_JOB_ERROR
 event.
 
+COLO_EXIT
+---------
+
+Emitted when VM finishes COLO mode due to some errors happening or
+at the request of users.
+
+Data:
+
+ - "mode": COLO mode, primary or secondary side (json-string)
+ - "reason":  the exit reason, internal error or external request. 
(json-string)
+ - "error": error message (json-string, operation)
+
+Example:
+
+{"timestamp": {"seconds": 2032141960, "microseconds": 417172},
+ "event": "COLO_EXIT", "data": {"mode": "primary", "reason": "request" } }
+
 DEVICE_DELETED
 --------------
 
diff --git a/migration/colo.c b/migration/colo.c
index 1e6d3dd..4cd7b00 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -18,6 +18,7 @@
 #include "qemu/error-report.h"
 #include "qemu/sockets.h"
 #include "migration/failover.h"
+#include "qapi-event.h"
 
 /*
  * The delay time before qemu begin the procedure of default failover 
treatment.
@@ -334,6 +335,9 @@ out:
     current_time = error_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
     if (ret < 0) {
         error_report("%s: %s", __func__, strerror(-ret));
+        qapi_event_send_colo_exit(COLO_MODE_PRIMARY, COLO_EXIT_REASON_ERROR,
+                                  true, strerror(-ret), NULL);
+
         /* Give users time to get involved in this verdict */
         while (current_time - error_time <= DEFAULT_FAILOVER_DELAY) {
             if (failover_request_is_active()) {
@@ -350,6 +354,9 @@ out:
             failover_request_active(NULL);
         }
         qemu_mutex_unlock_iothread();
+    } else {
+        qapi_event_send_colo_exit(COLO_MODE_PRIMARY, COLO_EXIT_REASON_REQUEST,
+                                  false, NULL, NULL);
     }
 
     qsb_free(buffer);
@@ -530,6 +537,9 @@ out:
     if (ret < 0) {
         error_report("colo incoming thread will exit, detect error: %s",
                      strerror(-ret));
+        qapi_event_send_colo_exit(COLO_MODE_SECONDARY, COLO_EXIT_REASON_ERROR,
+                                  true, strerror(-ret), NULL);
+
         /* Give users time to get involved in this verdict */
         while (current_time - error_time <= DEFAULT_FAILOVER_DELAY) {
             if (failover_request_is_active()) {
@@ -548,6 +558,9 @@ out:
             error_report("SVM is going to exit in default!");
             exit(1);
         }
+    } else {
+        qapi_event_send_colo_exit(COLO_MODE_SECONDARY, 
COLO_EXIT_REASON_REQUEST,
+                                  false, NULL, NULL);
     }
 
     if (fb) {
diff --git a/qapi-schema.json b/qapi-schema.json
index 2ed63e0..981e9b2 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -782,6 +782,22 @@
   'data': [ 'unknown', 'primary', 'secondary'] }
 
 ##
+# @COLOExitReason
+#
+# The reason for a COLO exit
+#
+# @unknown: unknown reason
+#
+# @request: COLO exit is due to an external request
+#
+# @error: COLO exit is due to an internal error
+#
+# Since: 2.6
+##
+{ 'enum': 'COLOExitReason',
+  'data': [ 'unknown', 'request', 'error'] }
+
+##
 # @x-colo-lost-heartbeat
 #
 # Tell qemu that heartbeat is lost, request it to do takeover procedures.
diff --git a/qapi/event.json b/qapi/event.json
index f0cef01..f63d456 100644
--- a/qapi/event.json
+++ b/qapi/event.json
@@ -255,6 +255,23 @@
   'data': {'status': 'MigrationStatus'}}
 
 ##
+# @COLO_EXIT
+#
+# Emitted when VM finishes COLO mode due to some errors happening or
+# at the request of users.
+#
+# @mode: which COLO mode the VM was in when it exited.
+#
+# @reason: describes the reason for the COLO exit.
+#
+# @error: #optional, error message. Only present on error happening.
+#
+# Since: 2.6
+##
+{ 'event': 'COLO_EXIT',
+  'data': {'mode': 'COLOMode', 'reason': 'COLOExitReason', '*error': 'str' } }
+
+##
 # @ACPI_DEVICE_OST
 #
 # Emitted when guest executes ACPI _OST method.
-- 
1.8.3.1