[libvirt] [PATCH] virsh: use keepalive protocol in virsh for migration

[Guannan Ren]

Bugzilla:https://bugzilla.redhat.com/show_bug.cgi?id=822839
For non-p2p migration, if the network is down in the process of migrate,
The virsh client will hang up for a fair long time. The patch will add
keepalive into virsh to determine the status of network connection with
remote libvirtd, aboring migration job after 30 seconds later since
disconnection.
---
 tools/virsh.c |   29 +++++++++++++++++++++++------
 1 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/tools/virsh.c b/tools/virsh.c
index 5226bd8..9099328 100644
--- a/tools/virsh.c
+++ b/tools/virsh.c
@@ -414,13 +414,14 @@ typedef struct __vshCtrlData {
     vshControl *ctl;
     const vshCmd *cmd;
     int writefd;
+    virConnectPtr dconn;
 } vshCtrlData;
 
 typedef void (*jobWatchTimeoutFunc) (vshControl *ctl, virDomainPtr dom,
                                      void *opaque);
 
 static bool
-vshWatchJob(vshControl *ctl,
+vshWatchJob(vshCtrlData *data,
             virDomainPtr dom,
             bool verbose,
             int pipe_fd,
@@ -3277,6 +3278,7 @@ cmdSave(vshControl *ctl, const vshCmd *cmd)
     data.ctl = ctl;
     data.cmd = cmd;
     data.writefd = p[1];
+    data.dconn = NULL;
 
     if (virThreadCreate(&workerThread,
                         true,
@@ -3284,7 +3286,7 @@ cmdSave(vshControl *ctl, const vshCmd *cmd)
                         &data) < 0)
         goto cleanup;
 
-    ret = vshWatchJob(ctl, dom, verbose, p[0], 0, NULL, NULL, _("Save"));
+    ret = vshWatchJob(&data, dom, verbose, p[0], 0, NULL, NULL, _("Save"));
 
     virThreadJoin(&workerThread);
 
@@ -3584,6 +3586,7 @@ cmdManagedSave(vshControl *ctl, const vshCmd *cmd)
     data.ctl = ctl;
     data.cmd = cmd;
     data.writefd = p[1];
+    data.dconn = NULL;
 
     if (virThreadCreate(&workerThread,
                         true,
@@ -3591,7 +3594,7 @@ cmdManagedSave(vshControl *ctl, const vshCmd *cmd)
                         &data) < 0)
         goto cleanup;
 
-    ret = vshWatchJob(ctl, dom, verbose, p[0], 0,
+    ret = vshWatchJob(&data, dom, verbose, p[0], 0,
                       NULL, NULL, _("Managedsave"));
 
     virThreadJoin(&workerThread);
@@ -4062,6 +4065,7 @@ cmdDump(vshControl *ctl, const vshCmd *cmd)
     data.ctl = ctl;
     data.cmd = cmd;
     data.writefd = p[1];
+    data.dconn = NULL;
 
     if (virThreadCreate(&workerThread,
                         true,
@@ -4069,7 +4073,7 @@ cmdDump(vshControl *ctl, const vshCmd *cmd)
                         &data) < 0)
         goto cleanup;
 
-    ret = vshWatchJob(ctl, dom, verbose, p[0], 0, NULL, NULL, _("Dump"));
+    ret = vshWatchJob(&data, dom, verbose, p[0], 0, NULL, NULL, _("Dump"));
 
     virThreadJoin(&workerThread);
 
@@ -7189,6 +7193,10 @@ doMigrate (void *opaque)
         dconn = virConnectOpenAuth (desturi, virConnectAuthPtrDefault, 0);
         if (!dconn) goto out;
 
+        data->dconn = dconn;
+        if (virConnectSetKeepAlive(dconn, 5, 5) < 0)
+             vshDebug(ctl, VSH_ERR_WARNING, "migrate: Failed to start keepalive\n");
+
         ddom = virDomainMigrate2(dom, dconn, xml, flags, dname, migrateuri, 0);
         if (ddom) {
             virDomainFree(ddom);
@@ -7244,7 +7252,7 @@ vshMigrationTimeout(vshControl *ctl,
 }
 
 static bool
-vshWatchJob(vshControl *ctl,
+vshWatchJob(vshCtrlData *data,
             virDomainPtr dom,
             bool verbose,
             int pipe_fd,
@@ -7262,6 +7270,7 @@ vshWatchJob(vshControl *ctl,
     char retchar;
     bool functionReturn = false;
     sigset_t sigmask, oldsigmask;
+    vshControl *ctl = data->ctl;
 
     sigemptyset(&sigmask);
     sigaddset(&sigmask, SIGINT);
@@ -7305,6 +7314,13 @@ repoll:
             goto cleanup;
         }
 
+       if (data->dconn && virConnectIsAlive(data->dconn) <= 0) {
+            virDomainAbortJob(dom);
+            vshError(ctl, "%s",
+                      _("Lost connection to destination host"));
+            goto cleanup;
+        }
+
         GETTIMEOFDAY(&curr);
         if (timeout && (((int)(curr.tv_sec - start.tv_sec)  * 1000 +
                          (int)(curr.tv_usec - start.tv_usec) / 1000) >
@@ -7378,13 +7394,14 @@ cmdMigrate(vshControl *ctl, const vshCmd *cmd)
     data.ctl = ctl;
     data.cmd = cmd;
     data.writefd = p[1];
+    data.dconn = NULL;
 
     if (virThreadCreate(&workerThread,
                         true,
                         doMigrate,
                         &data) < 0)
         goto cleanup;
-    functionReturn = vshWatchJob(ctl, dom, verbose, p[0], timeout,
+    functionReturn = vshWatchJob(&data, dom, verbose, p[0], timeout,
                                  vshMigrationTimeout, NULL, _("Migration"));
 
     virThreadJoin(&workerThread);
-- 
1.7.7.5