migration: add trace point when vm_stop_force_state fails

This is a critical failure scenario for migration that is hard to
diagnose from existing probes. Most likely it is caused by an error
from bdrv_flush(), but we're not logging the errno anywhere, hence
this new probe.

Reviewed-by: Connor Kuehl <ckuehl@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>

diff --git a/migration/migration.c b/migration/migration.c
index 4828997f63dc88d27cc994c5ad21277d36653c2d..4228635d18806dc419677ccbde54c7b067baf831 100644 (file)
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -3115,6 +3115,7 @@ static void migration_completion(MigrationState *s)
         if (!ret) {
             bool inactivate = !migrate_colo_enabled();
             ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
+            trace_migration_completion_vm_stop(ret);
             if (ret >= 0) {
                 ret = migration_maybe_pause(s, &current_active_state,
                                             MIGRATION_STATUS_DEVICE);

diff --git a/migration/trace-events b/migration/trace-events
index 860c4f40250fba1678e7e8a1c2f04fa2e374429a..a1c0f034ab8c0798a38b214f1e3294a23712f6df 100644 (file)
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -149,6 +149,7 @@ migrate_pending(uint64_t size, uint64_t max, uint64_t pre, uint64_t compat, uint
 migrate_send_rp_message(int msg_type, uint16_t len) "%d: len %d"
 migrate_send_rp_recv_bitmap(char *name, int64_t size) "block '%s' size 0x%"PRIi64
 migration_completion_file_err(void) ""
+migration_completion_vm_stop(int ret) "ret %d"
 migration_completion_postcopy_end(void) ""
 migration_completion_postcopy_end_after_complete(void) ""
 migration_rate_limit_pre(int ms) "%d ms"