qemu: Report error from both sides of migration

When migration fails in Perform phase, we call Finish on the destination
host with cancelled=1 and get the error from there and report it to the
user. This works well if the error on the destination caused the
migration to fail. But in other cases the main error may reported by the
source and the destination would just be complaining about broken
migration stream.

In other words, we don't really know which error caused the migration to
fail and we have no way of detecting that. So instead of choosing one
error, this patch will combine the error messages from both sides of
migration into a single message and report it to the user. The result
would be, for example:

    operation failed: migration failed. Message from the source host:
    operation failed: job 'migration out' failed: Certificate does not
    match the hostname ble.bla. Message from the destination host:
    operation failed: job 'migration in' failed: load of migration
    failed: Invalid argument

And yes, this is ugly, but I wasn't able to come up with a better way of
fixing this issue.

https://issues.redhat.com/browse/RHEL-58933

Signed-off-by: Jiri Denemark <jdenemar@redhat.com>
Reviewed-by: Ján Tomko <jtomko@redhat.com>

diff --git a/src/libvirt-domain.c b/src/libvirt-domain.c
index e8e5379672aea94fb220e18cc11c6b27ddce6cbb..efccafc4d2f2c7b5c8f2571bd6c58c8cf2f965b1 100644 (file)
--- a/src/libvirt-domain.c
+++ b/src/libvirt-domain.c
@@ -3430,26 +3430,26 @@ virDomainMigrateVersion3Full(virDomainPtr domain,
         if (ddomain) {
             VIR_ERROR(_("finish step ignored that migration was cancelled"));
         } else {
-            /* If Finish reported a useful error, use it instead of the
-             * original "migration unexpectedly failed" error.
+            virErrorPtr err = virGetLastError();
+            /* When both Confirm and Finish reported an error in QEMU driver,
+             * we don't really know which error is the root cause. Let's report
+             * both errors to the user.
              *
              * This is ugly but we can't do better with the APIs we have. We
              * only replace the error if Finish was called with cancelled == 1
              * and reported a real error (old libvirt would report an error
-             * from RPC instead of MIGRATE_FINISH_OK), which only happens when
-             * the domain died on destination. To further reduce a possibility
-             * of false positives we also check that Perform returned
-             * VIR_ERR_OPERATION_FAILED.
+             * from RPC instead of MIGRATE_FINISH_OK).
              */
             if (orig_err &&
                 orig_err->domain == VIR_FROM_QEMU &&
-                orig_err->code == VIR_ERR_OPERATION_FAILED) {
-                virErrorPtr err = virGetLastError();
-                if (err &&
-                    err->domain == VIR_FROM_QEMU &&
-                    err->code != VIR_ERR_MIGRATE_FINISH_OK) {
-                    g_clear_pointer(&orig_err, virFreeError);
-                }
+                orig_err->code == VIR_ERR_OPERATION_FAILED &&
+                err &&
+                err->domain == VIR_FROM_QEMU &&
+                err->code != VIR_ERR_MIGRATE_FINISH_OK) {
+                virReportError(VIR_ERR_OPERATION_FAILED,
+                               _("migration failed. Message from the source host: %1$s. Message from the destination host: %2$s"),
+                               orig_err->message, err->message);
+                g_clear_pointer(&orig_err, virFreeError);
             }
         }
     }

diff --git a/src/qemu/qemu_migration.c b/src/qemu/qemu_migration.c
index 1582a738a3d881ff750de62fed56aaf77b803566..8c0e522828e1521d113ca4cfeef301ff6782a6ef 100644 (file)
--- a/src/qemu/qemu_migration.c
+++ b/src/qemu/qemu_migration.c
@@ -5904,26 +5904,26 @@ qemuMigrationSrcPerformPeer2Peer3(virQEMUDriver *driver,
         if (ddomain) {
             VIR_ERROR(_("finish step ignored that migration was cancelled"));
         } else {
-            /* If Finish reported a useful error, use it instead of the
-             * original "migration unexpectedly failed" error.
+            virErrorPtr err = virGetLastError();
+            /* When both Confirm and Finish reported an error in QEMU driver,
+             * we don't really know which error is the root cause. Let's report
+             * both errors to the user.
              *
              * This is ugly but we can't do better with the APIs we have. We
              * only replace the error if Finish was called with cancelled == 1
              * and reported a real error (old libvirt would report an error
-             * from RPC instead of MIGRATE_FINISH_OK), which only happens when
-             * the domain died on destination. To further reduce a possibility
-             * of false positives we also check that Perform returned
-             * VIR_ERR_OPERATION_FAILED.
+             * from RPC instead of MIGRATE_FINISH_OK).
              */
             if (orig_err &&
                 orig_err->domain == VIR_FROM_QEMU &&
-                orig_err->code == VIR_ERR_OPERATION_FAILED) {
-                virErrorPtr err = virGetLastError();
-                if (err &&
-                    err->domain == VIR_FROM_QEMU &&
-                    err->code != VIR_ERR_MIGRATE_FINISH_OK) {
-                    g_clear_pointer(&orig_err, virFreeError);
-                }
+                orig_err->code == VIR_ERR_OPERATION_FAILED &&
+                err &&
+                err->domain == VIR_FROM_QEMU &&
+                err->code != VIR_ERR_MIGRATE_FINISH_OK) {
+                virReportError(VIR_ERR_OPERATION_FAILED,
+                               _("migration failed. Message from the source host: %1$s. Message from the destination host: %2$s"),
+                               orig_err->message, err->message);
+                g_clear_pointer(&orig_err, virFreeError);
             }
         }
     }