[Qemu-devel] [PATCH COLO-Frame v8 11/34] COLO: Save VM state to slave when do checkpoint

[zhanghailiang]

We should save PVM's RAM/device to slave when needed.

For VM state, we will cache them in slave, we use QEMUSizedBuffer
to store the data, we need know the data size of VM state, so in master,
we use qsb to store VM state temporarily, and then migrate the data to
slave.

Signed-off-by: zhanghailiang <address@hidden>
Signed-off-by: Yang Hongyang <address@hidden>
Signed-off-by: Gonglei <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
---
 include/migration/migration.h |  7 +++++
 migration/colo.c              | 60 ++++++++++++++++++++++++++++++++++++++++---
 migration/ram.c               | 46 +++++++++++++++++++++++++--------
 migration/savevm.c            |  2 +-
 4 files changed, 101 insertions(+), 14 deletions(-)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index 0548371..f14c321 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -66,6 +66,11 @@ MigrationIncomingState *migration_incoming_get_current(void);
 MigrationIncomingState *migration_incoming_state_new(QEMUFile *f);
 void migration_incoming_state_destroy(void);
 
+typedef struct COLOState COLOState;
+struct COLOState {
+    QEMUSizedBuffer *buffer;
+};
+
 struct MigrationState
 {
     int64_t bandwidth_limit;
@@ -88,6 +93,8 @@ struct MigrationState
     int64_t xbzrle_cache_size;
     int64_t setup_time;
     int64_t dirty_sync_count;
+
+    COLOState colo_state;
 };
 
 void migrate_set_state(int *state, int old_state, int new_state);
diff --git a/migration/colo.c b/migration/colo.c
index 4ba6f65..a77f23b 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -65,6 +65,8 @@ const char * const COLOCommand_lookup[] = {
 };
 
 static QEMUBH *colo_bh;
+/* colo buffer */
+#define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024)
 
 bool colo_supported(void)
 {
@@ -139,6 +141,8 @@ static int colo_ctl_get(QEMUFile *f, uint64_t require)
 static int colo_do_checkpoint_transaction(MigrationState *s, QEMUFile *control)
 {
     int ret;
+    size_t size;
+    QEMUFile *trans = NULL;
 
     ret = colo_ctl_put(s->file, COLO_CHECKPOINT_NEW);
     if (ret < 0) {
@@ -149,15 +153,47 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s, QEMUFile *control)
     if (ret < 0) {
         goto out;
     }
+    /* Reset colo buffer and open it for write */
+    qsb_set_length(s->colo_state.buffer, 0);
+    trans = qemu_bufopen("w", s->colo_state.buffer);
+    if (!trans) {
+        error_report("Open colo buffer for write failed");
+        goto out;
+    }
+
+    /* suspend and save vm state to colo buffer */
+    qemu_mutex_lock_iothread();
+    vm_stop_force_state(RUN_STATE_COLO);
+    qemu_mutex_unlock_iothread();
+    trace_colo_vm_state_change("run", "stop");
+
+    /* Disable block migration */
+    s->params.blk = 0;
+    s->params.shared = 0;
+    qemu_savevm_state_begin(trans, &s->params);
+    qemu_mutex_lock_iothread();
+    qemu_savevm_state_complete(trans);
+    qemu_mutex_unlock_iothread();
 
-    /* TODO: suspend and save vm state to colo buffer */
+    qemu_fflush(trans);
 
     ret = colo_ctl_put(s->file, COLO_CHECKPOINT_SEND);
     if (ret < 0) {
         goto out;
     }
+    /* we send the total size of the vmstate first */
+    size = qsb_get_length(s->colo_state.buffer);
+    ret = colo_ctl_put(s->file, size);
+    if (ret < 0) {
+        goto out;
+    }
 
-    /* TODO: send vmstate to Secondary */
+    qsb_put_buffer(s->file, s->colo_state.buffer, size);
+    qemu_fflush(s->file);
+    ret = qemu_file_get_error(s->file);
+    if (ret < 0) {
+        goto out;
+    }
 
     ret = colo_ctl_get(control, COLO_CHECKPOINT_RECEIVED);
     if (ret < 0) {
@@ -169,9 +205,18 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s, QEMUFile *control)
         goto out;
     }
 
-    /* TODO: resume Primary */
+    ret = 0;
+    /* resume master */
+    qemu_mutex_lock_iothread();
+    vm_start();
+    qemu_mutex_unlock_iothread();
+    trace_colo_vm_state_change("stop", "run");
 
 out:
+    if (trans) {
+        qemu_fclose(trans);
+    }
+
     return ret;
 }
 
@@ -196,6 +241,12 @@ static void *colo_thread(void *opaque)
         goto out;
     }
 
+    s->colo_state.buffer = qsb_create(NULL, COLO_BUFFER_BASE_SIZE);
+    if (s->colo_state.buffer == NULL) {
+        error_report("Failed to allocate colo buffer!");
+        goto out;
+    }
+
     qemu_mutex_lock_iothread();
     vm_start();
     qemu_mutex_unlock_iothread();
@@ -212,6 +263,9 @@ out:
     migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
                       MIGRATION_STATUS_COMPLETED);
 
+    qsb_free(s->colo_state.buffer);
+    s->colo_state.buffer = NULL;
+
     if (colo_control) {
         qemu_fclose(colo_control);
     }
diff --git a/migration/ram.c b/migration/ram.c
index 7f007e6..68980be 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -38,6 +38,7 @@
 #include "trace.h"
 #include "exec/ram_addr.h"
 #include "qemu/rcu_queue.h"
+#include "migration/colo.h"
 
 #ifdef DEBUG_MIGRATION_RAM
 #define DPRINTF(fmt, ...) \
@@ -1090,15 +1091,8 @@ void migration_bitmap_extend(ram_addr_t old, ram_addr_t 
new)
     }
 }
 
-/* Each of ram_save_setup, ram_save_iterate and ram_save_complete has
- * long-running RCU critical section.  When rcu-reclaims in the code
- * start to become numerous it will be necessary to reduce the
- * granularity of these critical sections.
- */
-
-static int ram_save_setup(QEMUFile *f, void *opaque)
+static int ram_save_init_globals(void)
 {
-    RAMBlock *block;
     int64_t ram_bitmap_pages; /* Size of bitmap in pages, including gaps */
 
     mig_throttle_on = false;
@@ -1158,6 +1152,31 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     migration_bitmap_sync();
     qemu_mutex_unlock_ramlist();
     qemu_mutex_unlock_iothread();
+    rcu_read_unlock();
+
+    return 0;
+}
+
+/* Each of ram_save_setup, ram_save_iterate and ram_save_complete has
+ * long-running RCU critical section.  When rcu-reclaims in the code
+ * start to become numerous it will be necessary to reduce the
+ * granularity of these critical sections.
+ */
+
+static int ram_save_setup(QEMUFile *f, void *opaque)
+{
+    RAMBlock *block;
+
+    /*
+     * migration has already setup the bitmap, reuse it.
+     */
+    if (!migration_in_colo_state()) {
+        if (ram_save_init_globals() < 0) {
+            return -1;
+         }
+    }
+
+    rcu_read_lock();
 
     qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE);
 
@@ -1257,7 +1276,8 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
     while (true) {
         int pages;
 
-        pages = ram_find_and_save_block(f, true, &bytes_transferred);
+        pages = ram_find_and_save_block(f, !migration_in_colo_state(),
+                                        &bytes_transferred);
         /* no more blocks to sent */
         if (pages == 0) {
             break;
@@ -1268,8 +1288,14 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
     ram_control_after_iterate(f, RAM_CONTROL_FINISH);
 
     rcu_read_unlock();
+    /*
+     * Since we need to reuse dirty bitmap in colo,
+     * don't cleanup the bitmap.
+     */
+    if (!migrate_enable_colo() || migration_has_failed(migrate_get_current())) 
{
+        migration_end();
+    }
 
-    migration_end();
     qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
 
     return 0;
diff --git a/migration/savevm.c b/migration/savevm.c
index 81dbe58..7f91136 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -48,7 +48,7 @@
 #include "qemu/iov.h"
 #include "block/snapshot.h"
 #include "block/qapi.h"
-
+#include "migration/colo.h"
 
 #ifndef ETH_P_RARP
 #define ETH_P_RARP 0x8035
-- 
1.8.3.1