[Qemu-devel] [PATCH RFC v3 22/27] COLO: Do checkpoint according to the result of net packets comparing

[zhanghailiang]

Only do checkpoint, when the VMs' output net packets are inconsistent.

Signed-off-by: zhanghailiang <address@hidden>
Signed-off-by: Gao feng <address@hidden>
---
 include/net/colo-nic.h |  2 ++
 migration/colo.c       | 23 +++++++++++++++++++++++
 net/colo-nic.c         | 41 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 66 insertions(+)

diff --git a/include/net/colo-nic.h b/include/net/colo-nic.h
index 40dbcfb..67c9807 100644
--- a/include/net/colo-nic.h
+++ b/include/net/colo-nic.h
@@ -19,4 +19,6 @@ void colo_proxy_destroy(int side);
 void colo_add_nic_devices(NetClientState *nc);
 void colo_remove_nic_devices(NetClientState *nc);
 
+int colo_proxy_compare(void);
+
 #endif
diff --git a/migration/colo.c b/migration/colo.c
index 9f8a873..3e13611 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -24,6 +24,12 @@ do { fprintf(stdout, "colo: " fmt , ## __VA_ARGS__); } while 
(0)
 #else
 #define DPRINTF(fmt, ...) do {} while (0)
 #endif
+/*
+ * force checkpoint timer: unit ms
+ * this is large because COLO checkpoint will mostly depend on
+ * COLO compare module.
+ */
+#define CHKPOINT_TIMER 10000
 
 enum {
     COLO_READY = 0x46,
@@ -321,6 +327,23 @@ static void *colo_thread(void *opaque)
     DPRINTF("vm resume to run\n");
 
     while (s->state == MIG_STATE_COLO) {
+        int proxy_checkpoint_req;
+
+        /* 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
+             */
+            usleep(1000);
+            continue;
+        } else {
+            DPRINTF("Net packets is not consistent!!!\n");
+        }
+
         /* start a colo checkpoint */
         if (do_colo_transaction(s, colo_control)) {
             goto out;
diff --git a/net/colo-nic.c b/net/colo-nic.c
index 38d9bf5..563d661 100644
--- a/net/colo-nic.c
+++ b/net/colo-nic.c
@@ -37,6 +37,9 @@ typedef struct nic_device {
     bool is_up;
 } nic_device;
 
+typedef struct colo_msg {
+    bool is_checkpoint;
+} colo_msg;
 
 typedef struct colo_proxy {
     int sockfd;
@@ -376,3 +379,41 @@ void colo_proxy_destroy(int side)
     cp_info.index = -1;
     colo_nic_side = -1;
 }
+/*
+do checkpoint: return 1
+error: return -1
+do not checkpoint: return 0
+*/
+int colo_proxy_compare(void)
+{
+    uint8_t *buff;
+    int64_t size;
+    struct nlmsghdr *h;
+    struct colo_msg *m;
+    int ret = -1;
+
+    size = colo_proxy_recv(&buff, MSG_DONTWAIT);
+
+    /* timeout, return no checkpoint message. */
+    if (size <= 0) {
+        return 0;
+    }
+
+    h = (struct nlmsghdr *) buff;
+
+    if (h->nlmsg_type == NLMSG_ERROR) {
+        goto out;
+    }
+
+    if (h->nlmsg_len < NLMSG_LENGTH(sizeof(*m))) {
+        goto out;
+    }
+
+    m = NLMSG_DATA(h);
+
+    ret = m->is_checkpoint ? 1 : 0;
+
+out:
+    g_free(buff);
+    return ret;
+}
-- 
1.7.12.4