[Qemu-devel] [PATCH COLO-Frame v6 16/31] qmp event: Add event notification for COLO error

[zhanghailiang]

If some errors happen during VM's COLO FT stage, it's import to notify the users
this event, Togehter 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 exit 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>
---
 docs/qmp/qmp-events.txt | 16 ++++++++++++++++
 migration/colo.c        | 12 ++++++++++--
 qapi/event.json         | 15 +++++++++++++++
 3 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/docs/qmp/qmp-events.txt b/docs/qmp/qmp-events.txt
index 4c13d48..7b6df2e 100644
--- a/docs/qmp/qmp-events.txt
+++ b/docs/qmp/qmp-events.txt
@@ -473,6 +473,22 @@ Example:
 { "timestamp": {"seconds": 1290688046, "microseconds": 417172},
   "event": "SPICE_MIGRATE_COMPLETED" }
 
+COLO_EXIT
+---------
+
+Emitted when VM finish COLO mode due to some errors happening or
+the request of users.
+
+Data: None.
+
+ - "mode": COLO mode, 'primary' or 'secondary'
+ - "error": Error message (json-string, optional)
+
+Example:
+
+{"timestamp": {"seconds": 2032141960, "microseconds": 417172},
+ "event": "COLO_EXIT", "data": {"mode": "primary"}}
+
 
 STOP
 ----
diff --git a/migration/colo.c b/migration/colo.c
index 3ecaec8..a65f9ea 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -15,6 +15,7 @@
 #include "trace.h"
 #include "qemu/error-report.h"
 #include "migration/migration-failover.h"
+#include "qapi-event.h"
 
 enum {
     COLO_CHECPOINT_READY = 0x46,
@@ -325,13 +326,14 @@ static void *colo_thread(void *opaque)
 
 out:
     error_report("colo: some error happens in colo_thread");
+    qapi_event_send_colo_exit("primary", true, "unknown", NULL);;
     /* Give users time (2s) to get involved in this verdict */
     for (i = 0; i < 10; i++) {
         if (failover_request_is_set()) {
             error_report("Primary VM will take over work");
             break;
         }
-        usleep(200*1000);
+        usleep(200 * 1000);
     }
     qemu_mutex_lock_iothread();
     if (!failover_request_is_set()) {
@@ -533,13 +535,19 @@ void *colo_process_incoming_checkpoints(void *opaque)
 
 out:
     error_report("Detect some error or get a failover request");
+    /*
+    * Here, we raise a qmp event to the user,
+    * It can help user to know what happens, and help deciding whether to
+    * do failover.
+    */
+    qapi_event_send_colo_exit("secondary", true, "unknown", NULL);;
     /* Give users time (2s) to get involved in this verdict */
     for (i = 0; i < 10; i++) {
         if (failover_request_is_set()) {
             error_report("Secondary VM will take over work");
             break;
         }
-        usleep(200*1000);
+        usleep(200 * 1000);
     }
     /* check flag again*/
     if (!failover_request_is_set()) {
diff --git a/qapi/event.json b/qapi/event.json
index 378dda5..e269765 100644
--- a/qapi/event.json
+++ b/qapi/event.json
@@ -243,6 +243,21 @@
 { 'event': 'SPICE_MIGRATE_COMPLETED' }
 
 ##
+# @COLO_EXIT
+#
+# Emitted when VM finish COLO mode due to some errors happening or
+# the request of users.
+#
+# @mode: 'primary' or 'secondeary'.
+#
+# @error:  #optional, error message. Only present on error happening.
+#
+# Since: 2.4
+##
+{ 'event': 'COLO_EXIT',
+  'data': {'mode': 'str', '*error':'str'}}
+
+##
 # @ACPI_DEVICE_OST
 #
 # Emitted when guest executes ACPI _OST method.
-- 
1.7.12.4