From: "Dr. David Alan Gilbert" <dgilb...@redhat.com>
An early postcopy failure can be recovered from as long as we know
we haven't sent the command to run the destination.
We have to undo the bdrv_inactivate_all by calling
bdrv_invalidate_cache_all
Note that I'm not using ms->block_inactive because once we've
sent the postcopy package we dont want anything else to try
and recover the block storage on the source; the destination
might have started writing to it.
Signed-off-by: Dr. David Alan Gilbert <dgilb...@redhat.com>
---
migration/migration.c | 25 +++++++++++++++++++++++++
1 file changed, 25 insertions(+)
diff --git a/migration/migration.c b/migration/migration.c
index 2766d2f..283677c 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1605,6 +1605,7 @@ static int postcopy_start(MigrationState *ms, bool
*old_vm_running)
QIOChannelBuffer *bioc;
QEMUFile *fb;
int64_t time_at_stop = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+ bool restart_block = false;
migrate_set_state(&ms->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_POSTCOPY_ACTIVE);
@@ -1624,6 +1625,7 @@ static int postcopy_start(MigrationState *ms, bool
*old_vm_running)
if (ret < 0) {
goto fail;
}
+ restart_block = true;
/*
* Cause any non-postcopiable, but iterative devices to
@@ -1680,6 +1682,18 @@ static int postcopy_start(MigrationState *ms, bool
*old_vm_running)
/* <><> end of stuff going into the package */
+ /* Last point of recovery; as soon as we send the package the destination
+ * can open devices and potentially start running.
+ * Lets just check again we've not got any errors.
+ */
+ ret = qemu_file_get_error(ms->to_dst_file);
+ if (ret) {
+ error_report("postcopy_start: Migration stream errored (pre package)");
+ goto fail_closefb;
+ }
+
+ restart_block = false;
+
/* Now send that blob */
if (qemu_savevm_send_packaged(ms->to_dst_file, bioc->data, bioc->usage)) {
goto fail_closefb;
@@ -1717,6 +1731,17 @@ fail_closefb:
fail:
migrate_set_state(&ms->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
MIGRATION_STATUS_FAILED);
+ if (restart_block) {
+ /* A failure happened early enough that we know the destination hasn't
+ * accessed block devices, so we're safe to recover.
+ */
+ Error *local_err = NULL;
+
+ bdrv_invalidate_cache_all(&local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ }
+ }
qemu_mutex_unlock_iothread();
return -1;
}
--
2.9.3
