[Qemu-devel] [PATCH COLO-Frame v11 39/39] COLO: Add block replication into colo process

[zhanghailiang]

Make sure master start block replication after slave's block replication 
started.

Signed-off-by: zhanghailiang <address@hidden>
Signed-off-by: Wen Congyang <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
---
 migration/colo.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 trace-events     |  2 ++
 2 files changed, 62 insertions(+)

diff --git a/migration/colo.c b/migration/colo.c
index b1b7905..c534ff9 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -20,6 +20,7 @@
 #include "migration/failover.h"
 #include "qapi-event.h"
 #include "net/filter.h"
+#include "block/block_int.h"
 
 /*
  * The delay time before qemu begin the procedure of default failover 
treatment.
@@ -62,6 +63,7 @@ static void secondary_vm_do_failover(void)
 {
     int old_state;
     MigrationIncomingState *mis = migration_incoming_get_current();
+    Error *local_err = NULL;
 
     /* Can not do failover during the process of VM's loading VMstate, Or
       * it will break the secondary VM.
@@ -79,6 +81,12 @@ static void secondary_vm_do_failover(void)
     migrate_set_state(&mis->state, MIGRATION_STATUS_COLO,
                       MIGRATION_STATUS_COMPLETED);
 
+    bdrv_stop_replication_all(true, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+    }
+    trace_colo_stop_block_replication("failover");
+
     if (!autostart) {
         error_report("\"-S\" qemu option will be ignored in secondary side");
         /* recover runstate to normal migration finish state */
@@ -110,6 +118,7 @@ static void primary_vm_do_failover(void)
 {
     MigrationState *s = migrate_get_current();
     int old_state;
+    Error *local_err = NULL;
 
     if (s->state != MIGRATION_STATUS_FAILED) {
         migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
@@ -134,6 +143,12 @@ static void primary_vm_do_failover(void)
     }
     /* Don't buffer any packets while exited COLO */
     qemu_set_default_filter_buffers(false);
+
+    bdrv_stop_replication_all(true, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+    }
+    trace_colo_stop_block_replication("failover");
 }
 
 void colo_do_failover(MigrationState *s)
@@ -212,6 +227,7 @@ static int colo_do_checkpoint_transaction(MigrationState *s,
     int colo_shutdown;
     size_t size;
     QEMUFile *trans = NULL;
+    Error *local_err = NULL;
 
     ret = colo_ctl_put(s->to_dst_file, COLO_COMMAND_CHECKPOINT_REQUEST, 0);
     if (ret < 0) {
@@ -250,6 +266,16 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s,
         goto out;
     }
 
+    /* we call this api although this may do nothing on primary side */
+    qemu_mutex_lock_iothread();
+    bdrv_do_checkpoint_all(&local_err);
+    qemu_mutex_unlock_iothread();
+    if (local_err) {
+        error_report_err(local_err);
+        ret = -1;
+        goto out;
+    }
+
     ret = colo_ctl_put(s->to_dst_file, COLO_COMMAND_VMSTATE_SEND, 0);
     if (ret < 0) {
         goto out;
@@ -296,6 +322,10 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s,
     qemu_release_default_filters_packets();
 
     if (colo_shutdown) {
+        qemu_mutex_lock_iothread();
+        bdrv_stop_replication_all(false, NULL);
+        trace_colo_stop_block_replication("shutdown");
+        qemu_mutex_unlock_iothread();
         colo_ctl_put(s->to_dst_file, COLO_COMMAND_GUEST_SHUTDOWN, 0);
         qemu_fflush(s->to_dst_file);
         colo_shutdown_requested = 0;
@@ -341,6 +371,7 @@ static void colo_process_checkpoint(MigrationState *s)
     int64_t error_time;
     int ret = 0;
     uint64_t value;
+    Error *local_err = NULL;
 
     failover_init_state();
 
@@ -376,6 +407,15 @@ static void colo_process_checkpoint(MigrationState *s)
     qemu_set_default_filter_buffers(true);
 
     qemu_mutex_lock_iothread();
+    /* start block replication */
+    bdrv_start_replication_all(REPLICATION_MODE_PRIMARY, &local_err);
+    if (local_err) {
+        qemu_mutex_unlock_iothread();
+        error_report_err(local_err);
+        ret = -EINVAL;
+        goto out;
+    }
+    trace_colo_start_block_replication();
     vm_start();
     qemu_mutex_unlock_iothread();
     trace_colo_vm_state_change("stop", "run");
@@ -492,6 +532,8 @@ static int colo_wait_handle_cmd(QEMUFile *f, int 
*checkpoint_request)
     case COLO_COMMAND_GUEST_SHUTDOWN:
         qemu_mutex_lock_iothread();
         vm_stop_force_state(RUN_STATE_COLO);
+        bdrv_stop_replication_all(false, NULL);
+        trace_colo_stop_block_replication("shutdown");
         qemu_system_shutdown_request_core();
         qemu_mutex_unlock_iothread();
         /* the main thread will exit and termiante the whole
@@ -524,6 +566,7 @@ void *colo_process_incoming_thread(void *opaque)
     int64_t error_time, current_time;
     int ret = 0;
     uint64_t value;
+    Error *local_err = NULL;
 
     migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
                       MIGRATION_STATUS_COLO);
@@ -560,6 +603,16 @@ void *colo_process_incoming_thread(void *opaque)
         goto out;
     }
 
+    qemu_mutex_lock_iothread();
+    /* start block replication */
+    bdrv_start_replication_all(REPLICATION_MODE_SECONDARY, &local_err);
+    qemu_mutex_unlock_iothread();
+    if (local_err) {
+        error_report_err(local_err);
+        goto out;
+    }
+    trace_colo_start_block_replication();
+
     ret = colo_ctl_put(mis->to_src_file, COLO_COMMAND_CHECKPOINT_READY, 0);
     if (ret < 0) {
         goto out;
@@ -639,6 +692,13 @@ void *colo_process_incoming_thread(void *opaque)
             qemu_mutex_unlock_iothread();
             goto out;
         }
+        /* discard colo disk buffer */
+        bdrv_do_checkpoint_all(&local_err);
+        qemu_mutex_unlock_iothread();
+        if (local_err) {
+            vmstate_loading = false;
+            goto out;
+        }
 
         vmstate_loading = false;
         qemu_mutex_unlock_iothread();
diff --git a/trace-events b/trace-events
index b80c1e0..5f95b3c 100644
--- a/trace-events
+++ b/trace-events
@@ -1583,6 +1583,8 @@ colo_vm_state_change(const char *old, const char *new) 
"Change '%s' => '%s'"
 colo_ctl_put(const char *msg, uint64_t value) "Send '%s' cmd, value: %" 
PRIu64""
 colo_ctl_get(const char *msg, uint64_t value) "Receive '%s' cmd, value: %" 
PRIu64""
 colo_failover_set_state(int new_state) "new state %d"
+colo_start_block_replication(void) "Block replication is started"
+colo_stop_block_replication(const char *reason) "Block replication is 
stopped(reason: '%s')"
 
 # kvm-all.c
 kvm_ioctl(int type, void *arg) "type 0x%x, arg %p"
-- 
1.8.3.1