[Qemu-devel] [PATCH COLO-Frame v17 28/34] COLO: Separate the process of saving/loading ram and device state

[zhanghailiang]

We separate the process of saving/loading ram and device state when do
checkpoint. We add new helpers for save/load ram/device. With this change,
we can directly transfer RAM from primary side to secondary side without
using channel-buffer as assistant, which also reduce the size of extra memory
was used during checkpoint.

Besides, we move the colo_flush_ram_cache to the proper position after the
above change.

Signed-off-by: zhanghailiang <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
Reviewed-by: Dr. David Alan Gilbert <address@hidden>
---
v16:
- Add Reviewd-by tag
v14:
- split two new patches from this patch
- Some minor fixes from Dave
v13:
- Re-use some existed helper functions to realize saving/loading
  ram and device.
v11:
- Remove load configuration section in qemu_loadvm_state_begin()
---
 migration/colo.c   | 48 ++++++++++++++++++++++++++++++++++++++----------
 migration/ram.c    |  5 -----
 migration/savevm.c |  4 ++++
 3 files changed, 42 insertions(+), 15 deletions(-)

diff --git a/migration/colo.c b/migration/colo.c
index 16f402f..5641031 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -284,21 +284,37 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s,
         goto out;
     }
 
+    colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
+    if (local_err) {
+        goto out;
+    }
+
     /* Disable block migration */
     s->params.blk = 0;
     s->params.shared = 0;
-    qemu_savevm_state_header(fb);
-    qemu_savevm_state_begin(fb, &s->params);
+    qemu_savevm_state_begin(s->to_dst_file, &s->params);
+    ret = qemu_file_get_error(s->to_dst_file);
+    if (ret < 0) {
+        error_report("Save vm state begin error");
+        goto out;
+    }
+
     qemu_mutex_lock_iothread();
-    qemu_savevm_state_complete_precopy(fb, false);
+    /*
+     * Only save VM's live state, which not including device state.
+     * TODO: We may need a timeout mechanism to prevent COLO process
+     * to be blocked here.
+     */
+    qemu_savevm_live_state(s->to_dst_file);
+    /* Note: device state is saved into buffer */
+    ret = qemu_save_device_state(fb);
     qemu_mutex_unlock_iothread();
-
-    qemu_fflush(fb);
-
-    colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
-    if (local_err) {
+    if (ret < 0) {
+        error_report("Save device state error");
         goto out;
     }
+    qemu_fflush(fb);
+
     /*
      * We need the size of the VMstate data in Secondary side,
      * With which we can decide how much data should be read.
@@ -565,6 +581,16 @@ void *colo_process_incoming_thread(void *opaque)
             goto out;
         }
 
+        ret = qemu_loadvm_state_begin(mis->from_src_file);
+        if (ret < 0) {
+            error_report("Load vm state begin error, ret=%d", ret);
+            goto out;
+        }
+        ret = qemu_loadvm_state_main(mis->from_src_file, mis);
+        if (ret < 0) {
+            error_report("Load VM's live state (ram) error");
+            goto out;
+        }
         /* read the VM state total size first */
         value = colo_receive_message_value(mis->from_src_file,
                                  COLO_MESSAGE_VMSTATE_SIZE, &local_err);
@@ -600,8 +626,10 @@ void *colo_process_incoming_thread(void *opaque)
         qemu_mutex_lock_iothread();
         qemu_system_reset(VMRESET_SILENT);
         vmstate_loading = true;
-        if (qemu_loadvm_state(fb) < 0) {
-            error_report("COLO: loadvm failed");
+        colo_flush_ram_cache();
+        ret = qemu_load_device_state(fb);
+        if (ret < 0) {
+            error_report("COLO: load device state failed");
             qemu_mutex_unlock_iothread();
             goto out;
         }
diff --git a/migration/ram.c b/migration/ram.c
index 91d1287..34aa87e 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -2466,7 +2466,6 @@ static int ram_load(QEMUFile *f, void *opaque, int 
version_id)
      * be atomic
      */
     bool postcopy_running = postcopy_state_get() >= 
POSTCOPY_INCOMING_LISTENING;
-    bool need_flush = false;
 
     seq_iter++;
 
@@ -2501,7 +2500,6 @@ static int ram_load(QEMUFile *f, void *opaque, int 
version_id)
             /* After going into COLO, we should load the Page into colo_cache 
*/
             if (ram_cache_enable) {
                 host = colo_cache_from_block_offset(block, addr);
-                need_flush = true;
             } else {
                 host = host_from_ram_block_offset(block, addr);
             }
@@ -2595,9 +2593,6 @@ static int ram_load(QEMUFile *f, void *opaque, int 
version_id)
 
     rcu_read_unlock();
 
-    if (!ret  && ram_cache_enable && need_flush) {
-        colo_flush_ram_cache();
-    }
     DPRINTF("Completed load of VM with exit code %d seq iteration "
             "%" PRIu64 "\n", ret, seq_iter);
     return ret;
diff --git a/migration/savevm.c b/migration/savevm.c
index 55a2eab..41ea2bd 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -911,6 +911,10 @@ void qemu_savevm_state_begin(QEMUFile *f,
             break;
         }
     }
+    if (migration_in_colo_state()) {
+        qemu_put_byte(f, QEMU_VM_EOF);
+        qemu_fflush(f);
+    }
 }
 
 /*
-- 
1.8.3.1