Force guest suspend at timeout

If the memory of guest OS is changed constantly, the live migration
can not be ended ever for ever.

We can use the command 'virsh migrate-setmaxdowntime' to control the
live migration. But the value of maxdowntime is diffcult to calculate
because it depends on the transfer speed of network and constantly
changing memroy size. We need a easy way to control the live migration.

This patch adds the support of forcing guest to suspend at timeout.
With this patch, when we migrate the guest OS, we can specify a
timeout. If the live migration timeouts, auto-suspend the guest OS,
where the migration will complete offline.

diff --git a/tools/virsh.c b/tools/virsh.c
index 8f3c59650dae0306f280de6e114470a079be1994..cd54174eb5a61764a94890d7e7a4ce7f12e0d37d 100644 (file)
--- a/tools/virsh.c
+++ b/tools/virsh.c
@@ -3418,6 +3418,7 @@ static const vshCmdOptDef opts_migrate[] = {
     {"desturi", VSH_OT_DATA, VSH_OFLAG_REQ, N_("connection URI of the destination host as seen from the client(normal migration) or source(p2p migration)")},
     {"migrateuri", VSH_OT_DATA, 0, N_("migration URI, usually can be omitted")},
     {"dname", VSH_OT_DATA, 0, N_("rename to new name during migration (if supported)")},
+    {"timeout", VSH_OT_INT, 0, N_("force guest to suspend if live migration exceeds timeout (in seconds)")},
     {NULL, 0, 0, NULL}
 };
 
@@ -3548,12 +3549,16 @@ cmdMigrate (vshControl *ctl, const vshCmd *cmd)
     int ret = -1;
     virThread workerThread;
     struct pollfd pollfd;
+    int found;
     char retchar;
     struct sigaction sig_action;
     struct sigaction old_sig_action;
     virDomainJobInfo jobinfo;
     bool verbose = false;
     sigset_t sigmask, oldsigmask;
+    int timeout;
+    struct timeval start, curr;
+    bool live_flag = false;
 
     vshCtrlData data;
 
@@ -3563,6 +3568,29 @@ cmdMigrate (vshControl *ctl, const vshCmd *cmd)
     if (vshCommandOptBool (cmd, "verbose"))
         verbose = true;
 
+    if (vshCommandOptBool (cmd, "live"))
+        live_flag = TRUE;
+    timeout = vshCommandOptInt(cmd, "timeout", &found);
+    if (found) {
+        if (! live_flag) {
+            vshError(ctl, "%s", _("migrate: Unexpected timeout for offline migration"));
+            goto cleanup;
+        }
+
+        if (timeout < 1) {
+            vshError(ctl, "%s", _("migrate: Invalid timeout"));
+            goto cleanup;
+        }
+
+        /* Ensure that we can multiply by 1000 without overflowing. */
+        if (timeout > INT_MAX / 1000) {
+            vshError(ctl, "%s", _("migrate: Timeout is too big"));
+            goto cleanup;
+        }
+    } else {
+        timeout = 0;
+    }
+
     if (pipe(p) < 0)
         goto cleanup;
 
@@ -3588,6 +3616,7 @@ cmdMigrate (vshControl *ctl, const vshCmd *cmd)
     sigemptyset(&sigmask);
     sigaddset(&sigmask, SIGINT);
 
+    GETTIMEOFDAY(&start);
     while (1) {
 repoll:
         ret = poll(&pollfd, 1, 500);
@@ -3618,6 +3647,15 @@ repoll:
             break;
         }
 
+        GETTIMEOFDAY(&curr);
+        if ( timeout && ((int)(curr.tv_sec - start.tv_sec)  * 1000 + \
+                         (int)(curr.tv_usec - start.tv_usec) / 1000) > timeout * 1000 ) {
+            /* suspend the domain when migration timeouts. */
+            vshDebug(ctl, 5, "suspend the domain when migration timeouts\n");
+            virDomainSuspend(dom);
+            timeout = 0;
+        }
+
         if (verbose) {
             pthread_sigmask(SIG_BLOCK, &sigmask, &oldsigmask);
             ret = virDomainGetJobInfo(dom, &jobinfo);

diff --git a/tools/virsh.pod b/tools/virsh.pod
index 3128d014570aceaeff7d8cff268a59401912ce66..c00cc8aba27943e4664f84b3a9c4a1401dcbbe23 100644 (file)
--- a/tools/virsh.pod
+++ b/tools/virsh.pod
@@ -490,7 +490,7 @@ type attribute for the <domain> element of XML.
 =item B<migrate> optional I<--live> I<--p2p> I<--direct> I<--tunnelled>
 I<--persistent> I<--undefinesource> I<--suspend> I<--copy-storage-all>
 I<--copy-storage-inc> I<--verbose> I<domain-id> I<desturi> I<migrateuri>
-I<dname>
+I<dname> I<--timeout>
 
 Migrate domain to another host.  Add I<--live> for live migration; I<--p2p>
 for peer-2-peer migration; I<--direct> for direct migration; or I<--tunnelled>
@@ -507,6 +507,9 @@ I<migrateuri> is the migration URI, which usually can be omitted.
 I<dname> is used for renaming the domain to new name during migration, which
 also usually can be omitted.
 
+I<--timeout> forces guest to suspend when live migration exceeds timeout, and
+then the migration will complete offline. It can only be used with I<--live>.
+
 B<Note>: The I<desturi> parameter for normal migration and peer2peer migration
 has different semantics: