[Qemu-devel] [PATCH COLO-Frame v9 12/32] COLO: Save PVM state to secondary side when do checkpoint

[zhanghailiang]

The main process of checkpoint is to synchronize SVM with PVM.
VM's state includes ram and device state. So we will migrate PVM's
state to SVM when do checkpoint, just like migration does.

We will cache PVM's state in slave, we use QEMUSizedBuffer
to store the data, we need to know the size of VM state, so in master,
we use qsb to store VM state temporarily, get the data size by call 
qsb_get_length()
and then migrate the data to the qsb in the secondary side.

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>
---
 migration/colo.c   | 70 +++++++++++++++++++++++++++++++++++++++++++++++++-----
 migration/ram.c    | 46 +++++++++++++++++++++++++++--------
 migration/savevm.c |  2 +-
 3 files changed, 101 insertions(+), 17 deletions(-)

diff --git a/migration/colo.c b/migration/colo.c
index 526ee85..f107032 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -18,6 +18,8 @@
 #include "qemu/sockets.h"
 
 static QEMUBH *colo_bh;
+/* colo buffer */
+#define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024)
 
 bool colo_supported(void)
 {
@@ -96,9 +98,12 @@ static int colo_ctl_get(QEMUFile *f, uint32_t require)
     return value;
 }
 
-static int colo_do_checkpoint_transaction(MigrationState *s)
+static int colo_do_checkpoint_transaction(MigrationState *s,
+                                          QEMUSizedBuffer *buffer)
 {
     int ret;
+    size_t size;
+    QEMUFile *trans = NULL;
 
     ret = colo_ctl_put(s->to_dst_file, COLO_CMD_CHECKPOINT_REQUEST, 0);
     if (ret < 0) {
@@ -109,15 +114,48 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s)
     if (ret < 0) {
         goto out;
     }
+    /* Reset colo buffer and open it for write */
+    qsb_set_length(buffer, 0);
+    trans = qemu_bufopen("w", 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_header(trans);
+    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->to_dst_file, COLO_CMD_VMSTATE_SEND, 0);
     if (ret < 0) {
         goto out;
     }
+    /* we send the total size of the vmstate first */
+    size = qsb_get_length(buffer);
+    ret = colo_ctl_put(s->to_dst_file, COLO_CMD_VMSTATE_SIZE, size);
+    if (ret < 0) {
+        goto out;
+    }
 
-    /* TODO: send vmstate to Secondary */
+    qsb_put_buffer(s->to_dst_file, buffer, size);
+    qemu_fflush(s->to_dst_file);
+    ret = qemu_file_get_error(s->to_dst_file);
+    if (ret < 0) {
+        goto out;
+    }
 
     ret = colo_ctl_get(s->from_dst_file, COLO_CMD_VMSTATE_RECEIVED);
     if (ret < 0) {
@@ -129,15 +167,25 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s)
         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;
 }
 
 static void *colo_thread(void *opaque)
 {
     MigrationState *s = opaque;
+    QEMUSizedBuffer *buffer = NULL;
     int fd, ret = 0;
 
     /* Dup the fd of to_dst_file */
@@ -162,6 +210,13 @@ static void *colo_thread(void *opaque)
         goto out;
     }
 
+    buffer = qsb_create(NULL, COLO_BUFFER_BASE_SIZE);
+    if (buffer == NULL) {
+        ret = -ENOMEM;
+        error_report("Failed to allocate buffer!");
+        goto out;
+    }
+
     qemu_mutex_lock_iothread();
     vm_start();
     qemu_mutex_unlock_iothread();
@@ -169,7 +224,7 @@ static void *colo_thread(void *opaque)
 
     while (s->state == MIGRATION_STATUS_COLO) {
         /* start a colo checkpoint */
-        ret = colo_do_checkpoint_transaction(s);
+        ret = colo_do_checkpoint_transaction(s, buffer);
         if (ret < 0) {
             goto out;
         }
@@ -182,7 +237,10 @@ out:
     migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
                       MIGRATION_STATUS_COMPLETED);
 
-    if (s->from_dst_file) {
+    qsb_free(buffer);
+    buffer = NULL;
+
+   if (s->from_dst_file) {
         qemu_fclose(s->from_dst_file);
     }
 
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 6071215..c1b40ce 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