[PATCHv2 4/4] qemu: Wire up better early error reporting

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



The previous patches added infrastructure to report better errors from
monitor in some cases. This patch finalizes this "feature" by enabling
this enhanced error reporting on early phases of VM startup. In these
phases the possibility of qemu producing a useful error message is
really high compared to running it during the whole life cycle. After
the start up is complete, the feature is disabled to provide the usual
error messages so that users are not confused by possibly irrelevant
messages that may be in the domain log.

The original motivation to do this enhancement is to capture errors when
using VFIO device passthrough, where qemu reports errors after the
monitor is initialized and the existing error catching code couldn't
catch this producing a unhelpful message:

 # virsh start test
 error: Failed to start domain test
 error: Unable to read from monitor: Connection reset by peer

With this change, the message is changed to:

 # virsh start test
 error: Failed to start domain test
 error: internal error: early end of file from monitor: possible problem:
 qemu-system-x86_64: -device vfio-pci,host=00:1a.0,id=hostdev0,bus=pci.0,addr=0x5: vfio: error, group 8 is not viable, please ensure all devices within the iommu_group are bound to their vfio bus driver.
 qemu-system-x86_64: -device vfio-pci,host=00:1a.0,id=hostdev0,bus=pci.0,addr=0x5: vfio: failed to get group 8
 qemu-system-x86_64: -device vfio-pci,host=00:1a.0,id=hostdev0,bus=pci.0,addr=0x5: Device 'vfio-pci' could not be initialized
---

Notes:
    Version 2:
    - don't leak mon in case setting of the logfd fails,
    -ignore errors if setting of the logfd fails

 src/qemu/qemu_process.c | 30 +++++++++++++++++++-----------
 1 file changed, 19 insertions(+), 11 deletions(-)

diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c
index 846cee6..2b9bfe3 100644
--- a/src/qemu/qemu_process.c
+++ b/src/qemu/qemu_process.c
@@ -1389,7 +1389,7 @@ static qemuMonitorCallbacks monitorCallbacks = {
 };

 static int
-qemuConnectMonitor(virQEMUDriverPtr driver, virDomainObjPtr vm)
+qemuConnectMonitor(virQEMUDriverPtr driver, virDomainObjPtr vm, int logfd)
 {
     qemuDomainObjPrivatePtr priv = vm->privateData;
     int ret = -1;
@@ -1415,6 +1415,9 @@ qemuConnectMonitor(virQEMUDriverPtr driver, virDomainObjPtr vm)
                           &monitorCallbacks,
                           driver);

+    if (mon)
+        ignore_value(qemuMonitorSetDomainLog(mon, logfd));
+
     virObjectLock(vm);
     priv->monStart = 0;

@@ -1794,11 +1797,11 @@ qemuProcessWaitForMonitor(virQEMUDriverPtr driver,
     virHashTablePtr paths = NULL;
     qemuDomainObjPrivatePtr priv;

-    if (!virQEMUCapsUsedQMP(qemuCaps)
-        && pos != -1) {
-        if ((logfd = qemuDomainOpenLog(driver, vm, pos)) < 0)
-            return -1;
+    if (pos != -1 &&
+        (logfd = qemuDomainOpenLog(driver, vm, pos)) < 0)
+        return -1;

+    if (logfd != -1 && !virQEMUCapsUsedQMP(qemuCaps)) {
         if (VIR_ALLOC_N(buf, buf_size) < 0)
             goto closelog;

@@ -1809,9 +1812,8 @@ qemuProcessWaitForMonitor(virQEMUDriverPtr driver,
     }

     VIR_DEBUG("Connect monitor to %p '%s'", vm, vm->def->name);
-    if (qemuConnectMonitor(driver, vm) < 0) {
+    if (qemuConnectMonitor(driver, vm, logfd) < 0)
         goto cleanup;
-    }

     /* Try to get the pty path mappings again via the monitor. This is much more
      * reliable if it's available.
@@ -1838,14 +1840,15 @@ cleanup:
         /* VM is dead, any other error raised in the interim is probably
          * not as important as the qemu cmdline output */
         if (virQEMUCapsUsedQMP(qemuCaps)) {
-            if ((logfd = qemuDomainOpenLog(driver, vm, pos)) < 0)
-                return -1;
-
             if (VIR_ALLOC_N(buf, buf_size) < 0)
                 goto closelog;
         }

         len = strlen(buf);
+        /* best effor seek - we need to reset to the original position, so that
+         * a possible read of the fd in the monitor code doesn't influence this
+         * error delivery option */
+        lseek(logfd, pos, SEEK_SET);
         qemuProcessReadLog(logfd, buf + len, buf_size - len - 1, 0, true);
         virReportError(VIR_ERR_INTERNAL_ERROR,
                        _("process exited while connecting to monitor: %s"),
@@ -3080,7 +3083,7 @@ qemuProcessReconnect(void *opaque)
     virObjectRef(obj);

     /* XXX check PID liveliness & EXE path */
-    if (qemuConnectMonitor(driver, obj) < 0)
+    if (qemuConnectMonitor(driver, obj, -1) < 0)
         goto error;

     /* Failure to connect to agent shouldn't be fatal */
@@ -4047,6 +4050,9 @@ int qemuProcessStart(virConnectPtr conn,
             goto cleanup;
     }

+    /* unset reporting errors from qemu log */
+    qemuMonitorSetDomainLog(priv->mon, -1);
+
     virCommandFree(cmd);
     VIR_FORCE_CLOSE(logfile);
     virObjectUnref(cfg);
@@ -4062,6 +4068,8 @@ cleanup:
     virBitmapFree(nodemask);
     virCommandFree(cmd);
     VIR_FORCE_CLOSE(logfile);
+    if (priv->mon)
+        qemuMonitorSetDomainLog(priv->mon, -1);
     qemuProcessStop(driver, vm, VIR_DOMAIN_SHUTOFF_FAILED, stop_flags);
     virObjectUnref(cfg);
     virObjectUnref(caps);
-- 
1.8.3.2

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




[Index of Archives]     [Virt Tools]     [Libvirt Users]     [Lib OS Info]     [Fedora Users]     [Fedora Desktop]     [Fedora SELinux]     [Big List of Linux Books]     [Yosemite News]     [KDE Users]     [Fedora Tools]