[Qemu-devel] [RFC PATCH] block/migration: Disable cache invalidate for incoming migration

[Alexey Kardashevskiy <aik@ozlabs.ru>]

When migrated using libvirt with "--copy-storage-all", at the end of
migration there is race between NBD mirroring task trying to do flush
and migration completion, both end up invalidating cache. Since qcow2
driver does not handle this situation very well, random crashes happen.

This disables the BDRV_O_INCOMING flag for the block device being migrated
and restores it when NBD task is done.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---


The commit log is not full and most likely incorrect as well
as the patch :) Please, help. Thanks!

The patch seems to fix the initial problem though.


btw is there any easy way to migrate one QEMU to another
using NBD (i.e. not using "migrate -b") and not using libvirt?
What would the command line be? Debugging with libvirt is real
pain :(


---
 block.c     | 17 ++++-------------
 migration.c |  1 -
 nbd.c       | 11 +++++++++++
 3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/block.c b/block.c
index c5a251c..ed72e0a 100644
--- a/block.c
+++ b/block.c
@@ -5073,6 +5073,10 @@ void bdrv_invalidate_cache_all(Error **errp)
     QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
         AioContext *aio_context = bdrv_get_aio_context(bs);
 
+        if (!(bs->open_flags & BDRV_O_INCOMING)) {
+            continue;
+        }
+
         aio_context_acquire(aio_context);
         bdrv_invalidate_cache(bs, &local_err);
         aio_context_release(aio_context);
@@ -5083,19 +5087,6 @@ void bdrv_invalidate_cache_all(Error **errp)
     }
 }
 
-void bdrv_clear_incoming_migration_all(void)
-{
-    BlockDriverState *bs;
-
-    QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
-        AioContext *aio_context = bdrv_get_aio_context(bs);
-
-        aio_context_acquire(aio_context);
-        bs->open_flags = bs->open_flags & ~(BDRV_O_INCOMING);
-        aio_context_release(aio_context);
-    }
-}
-
 int bdrv_flush(BlockDriverState *bs)
 {
     Coroutine *co;
diff --git a/migration.c b/migration.c
index 8d675b3..c49a05a 100644
--- a/migration.c
+++ b/migration.c
@@ -103,7 +103,6 @@ static void process_incoming_migration_co(void *opaque)
     }
     qemu_announce_self();
 
-    bdrv_clear_incoming_migration_all();
     /* Make sure all file formats flush their mutable metadata */
     bdrv_invalidate_cache_all(&local_err);
     if (local_err) {
diff --git a/nbd.c b/nbd.c
index e9b539b..7b479c0 100644
--- a/nbd.c
+++ b/nbd.c
@@ -106,6 +106,7 @@ struct NBDExport {
     off_t dev_offset;
     off_t size;
     uint32_t nbdflags;
+    bool restore_incoming;
     QTAILQ_HEAD(, NBDClient) clients;
     QTAILQ_ENTRY(NBDExport) next;
 
@@ -972,6 +973,13 @@ NBDExport *nbd_export_new(BlockDriverState *bs, off_t dev_offset,
     exp->ctx = bdrv_get_aio_context(bs);
     bdrv_ref(bs);
     bdrv_add_aio_context_notifier(bs, bs_aio_attached, bs_aio_detach, exp);
+
+    if (bs->open_flags & BDRV_O_INCOMING) {
+        bdrv_invalidate_cache(bs, NULL);
+        exp->restore_incoming = !!(bs->open_flags & BDRV_O_INCOMING);
+        bs->open_flags &= ~(BDRV_O_INCOMING);
+    }
+
     return exp;
 }
 
@@ -1021,6 +1029,9 @@ void nbd_export_close(NBDExport *exp)
     if (exp->bs) {
         bdrv_remove_aio_context_notifier(exp->bs, bs_aio_attached,
                                          bs_aio_detach, exp);
+        if (exp->restore_incoming) {
+            exp->bs->open_flags |= BDRV_O_INCOMING;
+        }
         bdrv_unref(exp->bs);
         exp->bs = NULL;
     }
-- 
2.0.0