Only do checkpoint, when the PVM's and SVM's output net packets are
inconsistent,
We also limit the min time between two continuous checkpoint action, to
give VM a change to run.
Signed-off-by: zhanghailiang <zhang.zhanghaili...@huawei.com>
Signed-off-by: Li Zhijian <lizhij...@cn.fujitsu.com>
---
include/net/colo-nic.h | 2 ++
migration/colo.c | 32 ++++++++++++++++++++++++++++++++
net/colo-nic.c | 5 +++++
3 files changed, 39 insertions(+)
diff --git a/include/net/colo-nic.h b/include/net/colo-nic.h
index 7b8ff57..271ab8b 100644
--- a/include/net/colo-nic.h
+++ b/include/net/colo-nic.h
@@ -30,4 +30,6 @@ void colo_remove_nic_devices(COLONicState *cns);
int colo_proxy_init(enum COLOMode mode);
void colo_proxy_destroy(enum COLOMode mode);
+int colo_proxy_compare(void);
+
#endif
diff --git a/migration/colo.c b/migration/colo.c
index c286152..f9f2156 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -19,6 +19,13 @@
#include "qapi-event.h"
#include "net/colo-nic.h"
+/*
+* We should not do checkpoint one after another without any time interval,
+* Because this will lead continuous 'stop' status for VM.
+* CHECKPOINT_MIN_PERIOD is the min time limit between two checkpoint action.
+*/
+#define CHECKPOINT_MIN_PERIOD 100 /* unit: ms */
+
/* Fix me: Convert to use QAPI */
typedef enum COLOCommand {
COLO_CHECPOINT_READY = 0x46,
@@ -341,6 +348,7 @@ static void *colo_thread(void *opaque)
{
MigrationState *s = opaque;
QEMUFile *colo_control = NULL;
+ int64_t current_time, checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
int i, ret;
failover_init_state();
@@ -376,15 +384,39 @@ static void *colo_thread(void *opaque)
trace_colo_vm_state_change("stop", "run");
while (s->state == MIGRATION_STATUS_COLO) {
+ int proxy_checkpoint_req;
+
if (failover_request_is_active()) {
error_report("failover request");
goto out;
}
+ /* wait for a colo checkpoint */
+ proxy_checkpoint_req = colo_proxy_compare();
+ if (proxy_checkpoint_req < 0) {
+ goto out;
+ } else if (!proxy_checkpoint_req) {
+ /*
+ * No checkpoint is needed, wait for 1ms and then
+ * check if we need checkpoint again
+ */
+ g_usleep(1000);
+ continue;
+ } else {
+ int64_t interval;
+
+ current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
+ interval = current_time - checkpoint_time;
+ if (interval < CHECKPOINT_MIN_PERIOD) {
+ /* Limit the min time between two checkpoint */
+ g_usleep((1000*(CHECKPOINT_MIN_PERIOD - interval)));
+ }
+ }
/* start a colo checkpoint */
if (colo_do_checkpoint_transaction(s, colo_control)) {
goto out;
}
+ checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
}
out:
diff --git a/net/colo-nic.c b/net/colo-nic.c
index 49380ce..d2073b8 100644
--- a/net/colo-nic.c
+++ b/net/colo-nic.c
@@ -427,3 +427,8 @@ void colo_proxy_destroy(enum COLOMode mode)
}
teardown_nic(mode, getpid());
}
+
+int colo_proxy_compare(void)
+{
+ return atomic_xchg(&packet_compare_different, 0);
+}
--
1.8.3.1
