COLO: fix setting checkpoint-delay not working properly

If we set checkpoint-delay through command 'migrate-set-parameters',
It will not take effect until we finish last sleep chekpoint-delay,
That's will be offensive espeically when we want to change its value
from an extreme big one to a proper value.

Fix it by using timer to realize checkpoint-delay.

Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Message-Id: <1484657864-21708-2-git-send-email-zhang.zhanghailiang@huawei.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

diff --git a/include/migration/colo.h b/include/migration/colo.h
index e32eef4763c063ca07d1d8f9e3da8044c8826820..2bbff9e6c2b54394d488edb680fdaf6832ad884b 100644 (file)
--- a/include/migration/colo.h
+++ b/include/migration/colo.h
@@ -35,4 +35,6 @@ COLOMode get_colo_mode(void);
 
 /* failover */
 void colo_do_failover(MigrationState *s);
+
+void colo_checkpoint_notify(void *opaque);
 #endif

diff --git a/include/migration/migration.h b/include/migration/migration.h
index 71ce19062cd1a6f8822ec405ac9f3a9e49ba38f6..cb83f1688e97111939d13ed4d84e075082c0eae5 100644 (file)
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -188,6 +188,11 @@ struct MigrationState
     /* The RAMBlock used in the last src_page_request */
     RAMBlock *last_req_rb;
 
+    /* The semaphore is used to notify COLO thread to do checkpoint */
+    QemuSemaphore colo_checkpoint_sem;
+    int64_t colo_checkpoint_time;
+    QEMUTimer *colo_delay_timer;
+
     /* The last error that occurred */
     Error *error;
 };

diff --git a/migration/colo.c b/migration/colo.c
index 93c85c538b6ebde50b0513f3b015b47622db724d..08b2e46dac74a5f5ced24334b981ce8d242e9348 100644 (file)
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -302,7 +302,7 @@ static void colo_process_checkpoint(MigrationState *s)
 {
     QIOChannelBuffer *bioc;
     QEMUFile *fb = NULL;
-    int64_t current_time, checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
+    int64_t current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
     Error *local_err = NULL;
     int ret;
 
@@ -332,26 +332,21 @@ static void colo_process_checkpoint(MigrationState *s)
     qemu_mutex_unlock_iothread();
     trace_colo_vm_state_change("stop", "run");
 
+    timer_mod(s->colo_delay_timer,
+            current_time + s->parameters.x_checkpoint_delay);
+
     while (s->state == MIGRATION_STATUS_COLO) {
         if (failover_get_state() != FAILOVER_STATUS_NONE) {
             error_report("failover request");
             goto out;
         }
 
-        current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
-        if (current_time - checkpoint_time <
-            s->parameters.x_checkpoint_delay) {
-            int64_t delay_ms;
+        qemu_sem_wait(&s->colo_checkpoint_sem);
 
-            delay_ms = s->parameters.x_checkpoint_delay -
-                       (current_time - checkpoint_time);
-            g_usleep(delay_ms * 1000);
-        }
         ret = colo_do_checkpoint_transaction(s, bioc, fb);
         if (ret < 0) {
             goto out;
         }
-        checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
     }
 
 out:
@@ -364,14 +359,32 @@ out:
         qemu_fclose(fb);
     }
 
+    timer_del(s->colo_delay_timer);
+
     if (s->rp_state.from_dst_file) {
         qemu_fclose(s->rp_state.from_dst_file);
     }
 }
 
+void colo_checkpoint_notify(void *opaque)
+{
+    MigrationState *s = opaque;
+    int64_t next_notify_time;
+
+    qemu_sem_post(&s->colo_checkpoint_sem);
+    s->colo_checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
+    next_notify_time = s->colo_checkpoint_time +
+                    s->parameters.x_checkpoint_delay;
+    timer_mod(s->colo_delay_timer, next_notify_time);
+}
+
 void migrate_start_colo_process(MigrationState *s)
 {
     qemu_mutex_unlock_iothread();
+    qemu_sem_init(&s->colo_checkpoint_sem, 0);
+    s->colo_delay_timer =  timer_new_ms(QEMU_CLOCK_HOST,
+                                colo_checkpoint_notify, s);
+
     migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
                       MIGRATION_STATUS_COLO);
     colo_process_checkpoint(s);

diff --git a/migration/migration.c b/migration/migration.c
index 2a26a20aafdd1c9834629a7cad850449f42bdede..c6ae69d3717448de37272e4c05a1d145df483046 100644 (file)
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -891,6 +891,9 @@ void qmp_migrate_set_parameters(MigrationParameters *params, Error **errp)
 
     if (params->has_x_checkpoint_delay) {
         s->parameters.x_checkpoint_delay = params->x_checkpoint_delay;
+        if (migration_in_colo_state()) {
+            colo_checkpoint_notify(s);
+        }
     }
 }