[PULL 15/18] multifd: Only flush once each full round of memory

[Juan Quintela]

We need to add a new flag to mean to flush at that point.
Notice that we still flush at the end of setup and at the end of
complete stages.

Signed-off-by: Juan Quintela <quintela@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>

---

Add missing qemu_fflush(), now it passes all tests always.
In the previous version, the check that changes the default value to
false got lost in some rebase.  Get it back.
---
 migration/migration.h |  3 +--
 migration/options.c   |  8 ++------
 migration/ram.c       | 28 +++++++++++++++++++++++++++-
 3 files changed, 30 insertions(+), 9 deletions(-)

diff --git a/migration/migration.h b/migration/migration.h
index e2247d708f..3a918514e7 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -412,8 +412,7 @@ struct MigrationState {
      * only need to do this flush after we have go through all the
      * dirty pages.  For historical reasons, we do that after each
      * section.  This is suboptimal (we flush too many times).
-     * Default value is false.  Setting this property has no effect
-     * until the patch that removes this comment.  (since 8.1)
+     * Default value is false. (since 8.1)
      */
     bool multifd_flush_after_each_section;
     /*
diff --git a/migration/options.c b/migration/options.c
index 690c8f718e..53b7fc5d5d 100644
--- a/migration/options.c
+++ b/migration/options.c
@@ -89,7 +89,7 @@ Property migration_properties[] = {
     DEFINE_PROP_BOOL("decompress-error-check", MigrationState,
                       decompress_error_check, true),
     DEFINE_PROP_BOOL("multifd-flush-after-each-section", MigrationState,
-                      multifd_flush_after_each_section, true),
+                      multifd_flush_after_each_section, false),
     DEFINE_PROP_UINT8("x-clear-bitmap-shift", MigrationState,
                       clear_bitmap_shift, CLEAR_BITMAP_SHIFT_DEFAULT),
     DEFINE_PROP_BOOL("x-preempt-pre-7-2", MigrationState,
@@ -341,11 +341,7 @@ bool migrate_multifd_flush_after_each_section(void)
 {
     MigrationState *s = migrate_get_current();
 
-    /*
-     * Until the patch that remove this comment, we always return that
-     * the property is enabled.
-     */
-    return true || s->multifd_flush_after_each_section;
+    return s->multifd_flush_after_each_section;
 }
 
 bool migrate_postcopy(void)
diff --git a/migration/ram.c b/migration/ram.c
index 1e2414d681..e9dcda8b9d 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -86,6 +86,7 @@
 #define RAM_SAVE_FLAG_XBZRLE   0x40
 /* 0x80 is reserved in qemu-file.h for RAM_SAVE_FLAG_HOOK */
 #define RAM_SAVE_FLAG_COMPRESS_PAGE    0x100
+#define RAM_SAVE_FLAG_MULTIFD_FLUSH    0x200
 /* We can't use any flag that is bigger than 0x200 */
 
 int (*xbzrle_encode_buffer_func)(uint8_t *, uint8_t *, int,
@@ -1581,6 +1582,7 @@ retry:
  * associated with the search process.
  *
  * Returns:
+ *         <0: An error happened
  *         PAGE_ALL_CLEAN: no dirty page found, give up
  *         PAGE_TRY_AGAIN: no dirty page found, retry for next block
  *         PAGE_DIRTY_FOUND: dirty page found
@@ -1608,6 +1610,15 @@ static int find_dirty_block(RAMState *rs, 
PageSearchStatus *pss)
         pss->page = 0;
         pss->block = QLIST_NEXT_RCU(pss->block, next);
         if (!pss->block) {
+            if (!migrate_multifd_flush_after_each_section()) {
+                QEMUFile *f = rs->pss[RAM_CHANNEL_PRECOPY].pss_channel;
+                int ret = multifd_send_sync_main(f);
+                if (ret < 0) {
+                    return ret;
+                }
+                qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
+                qemu_fflush(f);
+            }
             /*
              * If memory migration starts over, we will meet a dirtied page
              * which may still exists in compression threads's ring, so we
@@ -2600,6 +2611,9 @@ static int ram_find_and_save_block(RAMState *rs)
                     break;
                 } else if (res == PAGE_TRY_AGAIN) {
                     continue;
+                } else if (res < 0) {
+                    pages = res;
+                    break;
                 }
             }
         }
@@ -3286,6 +3300,10 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
         return ret;
     }
 
+    if (!migrate_multifd_flush_after_each_section()) {
+        qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
+    }
+
     qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
     qemu_fflush(f);
 
@@ -3471,6 +3489,9 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
         return ret;
     }
 
+    if (!migrate_multifd_flush_after_each_section()) {
+        qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
+    }
     qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
     qemu_fflush(f);
 
@@ -4152,7 +4173,9 @@ int ram_load_postcopy(QEMUFile *f, int channel)
             }
             decompress_data_with_multi_threads(f, page_buffer, len);
             break;
-
+        case RAM_SAVE_FLAG_MULTIFD_FLUSH:
+            multifd_recv_sync_main();
+            break;
         case RAM_SAVE_FLAG_EOS:
             /* normal exit */
             if (migrate_multifd_flush_after_each_section()) {
@@ -4426,6 +4449,9 @@ static int ram_load_precopy(QEMUFile *f)
                 break;
             }
             break;
+        case RAM_SAVE_FLAG_MULTIFD_FLUSH:
+            multifd_recv_sync_main();
+            break;
         case RAM_SAVE_FLAG_EOS:
             /* normal exit */
             if (migrate_multifd_flush_after_each_section()) {
-- 
2.40.0