qemu: Add timeout for monitor to avoid virsh getting stuck when monitor gets die.

[Mark Wu <dwu@xxxxxxxxxx>]

Hello Guys,

When the qemu process becomes hung,  virsh will get stuck on the hung 
guest and can't move forward.  It can be reproduced by the following steps:

1. setup a virt guest with qemu-kvm, and start it
2. stop qemu process with following:
 kill -STOP  `ps aux | grep qemu | grep -v grep | awk '{print $2}'`
3. run the following command:
virsh list

I think we can add a timeout for qemu monitor to resolve this problem: 
using virCondWaitUntil instead of virCondWait in qemuMonitorSend. What's 
your opinions?

Thanks!

diff --git a/src/qemu/qemu_monitor.c b/src/qemu/qemu_monitor.c
index fca8590..65d8de9 100644
--- a/src/qemu/qemu_monitor.c
+++ b/src/qemu/qemu_monitor.c
@@ -25,6 +25,7 @@
 
 #include <poll.h>
 #include <sys/un.h>
+#include <sys/time.h>
 #include <unistd.h>
 #include <fcntl.h>
 
@@ -691,11 +692,14 @@ int qemuMonitorClose(qemuMonitorPtr mon)
     return refs;
 }
 
+#define QEMU_JOB_WAIT_TIME (1000ull * 30)
 
 int qemuMonitorSend(qemuMonitorPtr mon,
                     qemuMonitorMessagePtr msg)
 {
     int ret = -1;
+    struct timeval now;
+    unsigned long long then;
 
     if (mon->eofcb) {
         msg->lastErrno = EIO;
@@ -706,7 +710,14 @@ int qemuMonitorSend(qemuMonitorPtr mon,
     qemuMonitorUpdateWatch(mon);
 
     while (!mon->msg->finished) {
-        if (virCondWait(&mon->notify, &mon->lock) < 0)
+       if (gettimeofday(&now, NULL) < 0) {
+               virReportSystemError(errno, "%s",
+                             _("cannot get time of day"));
+               return -1;
+       }
+       then = (now.tv_sec * 1000ull) + (now.tv_usec / 1000);
+       then += QEMU_JOB_WAIT_TIME;
+        if (virCondWaitUntil(&mon->notify, &mon->lock, then) < 0)
             goto cleanup;
     }

--
libvir-list mailing list
libvir-list@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/libvir-list