[PATCH v2 5/5] qemu: Use error from Finish instead of "unexpectedly failed"

[Jiri Denemark <jdenemar@xxxxxxxxxx>]

When QEMU exits on destination during migration, the source reports
either success (if the failure happened at the very end) or unhelpful
"unexpectedly failed" error message. However, the Finish API called on
the destination may report a real error so let's use it instead of the
generic one.

Signed-off-by: Jiri Denemark <jdenemar@xxxxxxxxxx>
---

Notes:
    Version 2:
    - cleaner control flow
    - more comments

 src/libvirt-domain.c      | 30 ++++++++++++++++++++++++++++--
 src/qemu/qemu_migration.c | 39 +++++++++++++++++++++++++++++++++++++--
 2 files changed, 65 insertions(+), 4 deletions(-)

diff --git a/src/libvirt-domain.c b/src/libvirt-domain.c
index 909c264..837933f 100644
--- a/src/libvirt-domain.c
+++ b/src/libvirt-domain.c
@@ -3175,8 +3175,34 @@ virDomainMigrateVersion3Full(virDomainPtr domain,
             (dconn, dname, cookiein, cookieinlen, &cookieout, &cookieoutlen,
              NULL, uri, destflags, cancelled);
     }
-    if (cancelled && ddomain)
-        VIR_ERROR(_("finish step ignored that migration was cancelled"));
+
+    if (cancelled) {
+        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.
+             *
+             * 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.
+             */
+            if (orig_err &&
+                orig_err->domain == VIR_FROM_QEMU &&
+                orig_err->code == VIR_ERR_OPERATION_FAILED) {
+                virErrorPtr err = virGetLastError();
+                if (err->domain == VIR_FROM_QEMU &&
+                    err->code != VIR_ERR_MIGRATE_FINISH_OK) {
+                    virFreeError(orig_err);
+                    orig_err = NULL;
+                }
+            }
+        }
+    }
 
     /* If ddomain is NULL, then we were unable to start
      * the guest on the target, and must restart on the
diff --git a/src/qemu/qemu_migration.c b/src/qemu/qemu_migration.c
index a9cbada..d789110 100644
--- a/src/qemu/qemu_migration.c
+++ b/src/qemu/qemu_migration.c
@@ -4982,8 +4982,34 @@ doPeer2PeerMigrate3(virQEMUDriverPtr driver,
              dconnuri, uri, destflags, cancelled);
         qemuDomainObjExitRemote(vm);
     }
-    if (cancelled && ddomain)
-        VIR_ERROR(_("finish step ignored that migration was cancelled"));
+
+    if (cancelled) {
+        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.
+             *
+             * 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.
+             */
+            if (orig_err &&
+                orig_err->domain == VIR_FROM_QEMU &&
+                orig_err->code == VIR_ERR_OPERATION_FAILED) {
+                virErrorPtr err = virGetLastError();
+                if (err->domain == VIR_FROM_QEMU &&
+                    err->code != VIR_ERR_MIGRATE_FINISH_OK) {
+                    virFreeError(orig_err);
+                    orig_err = NULL;
+                }
+            }
+        }
+    }
 
     /* If ddomain is NULL, then we were unable to start
      * the guest on the target, and must restart on the
@@ -5719,6 +5745,15 @@ qemuMigrationFinish(virQEMUDriverPtr driver,
         /* Guest is successfully running, so cancel previous auto destroy */
         qemuProcessAutoDestroyRemove(driver, vm);
     } else if (!(flags & VIR_MIGRATE_OFFLINE)) {
+        qemuDomainJobInfo info;
+
+        /* Check for a possible error on the monitor in case Finish was called
+         * earlier than monitor EOF handler got a chance to process the error
+         */
+        qemuMigrationFetchJobStatus(driver, vm,
+                                    QEMU_ASYNC_JOB_MIGRATION_IN,
+                                    &info);
+
         qemuProcessStop(driver, vm, VIR_DOMAIN_SHUTOFF_FAILED,
                         VIR_QEMU_PROCESS_STOP_MIGRATED);
         virDomainAuditStop(vm, "failed");
-- 
2.4.5

--
libvir-list mailing list
libvir-list@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/libvir-list