External/libvirt
1
0
Fork 0
mirror of https://gitlab.com/libvirt/libvirt.git synced 2024-07-30 21:47:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix now dead cleanup of VMs on libvirtd restart

Browse Source 
When libvirtd restarts it will attempt to reconnect to existing
LXC containers. If it loads a XML state file for the container
the container will appear running. If we fail to read the PID
file, or fail to connect to the LXC monitor, we should be killing
off the guest, but if the VMs cgroup does not exist any more,
cleanup will get skipped. Reading the PID file is also pointless
since the PID is in the XML statefile

In lxcReconnectVM we do not need to read the PID file. If part
of the reconnect process fails we need to run the VM terminate
code as a safety net.

In lxcVMTerminate, if we can't obtain the VM cgroup, we know
the process has died, but we must still run lxcVMCleanup to
clear out the virDomainObjPtr live state

* src/lxc/lxc_driver.c: Fix cleanup of dead VMs on restart
This commit is contained in:
Daniel P. Berrange 2011-07-15 15:33:15 +01:00
parent 2c32898c39
commit 80cafba310
1 changed files with 31 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
src/lxc/lxc_driver.c
View File

@ -1227,22 +1227,26 @@ static int lxcVmTerminate(lxc_driver_t *driver,
return -1;
}
if (virCgroupForDomain(driver->cgroup, vm->def->name, &group, 0) != 0)
return -1;
if (virCgroupForDomain(driver->cgroup, vm->def->name, &group, 0) == 0) {
rc = virCgroupKillPainfully(group);
if (rc < 0) {
virReportSystemError(-rc, "%s",
_("Failed to kill container PIDs"));
rc = -1;
goto cleanup;
}
if (rc == 1) {
lxcError(VIR_ERR_INTERNAL_ERROR, "%s",
_("Some container PIDs refused to die"));
rc = -1;
goto cleanup;
}
} else {
/* If cgroup doesn't exist, the VM pids must have already
* died and so we're just cleaning up stale state
*/
}
rc = virCgroupKillPainfully(group);
if (rc < 0) {
virReportSystemError(-rc, "%s",
_("Failed to kill container PIDs"));
rc = -1;
goto cleanup;
}
if (rc == 1) {
lxcError(VIR_ERR_INTERNAL_ERROR, "%s",
_("Some container PIDs refused to die"));
rc = -1;
goto cleanup;
}
lxcVmCleanup(driver, vm, reason);
rc = 0;
@ -2049,32 +2053,24 @@ lxcReconnectVM(void *payload, const void *name ATTRIBUTE_UNUSED, void *opaque)
lxcDomainObjPrivatePtr priv;
virDomainObjLock(vm);
VIR_DEBUG("Reconnect %d %d %d\n", vm->def->id, vm->pid, vm->state.state);
priv = vm->privateData;
if ((priv->monitor = lxcMonitorClient(driver, vm)) < 0) {
goto cleanup;
}
/* Read pid from controller */
if ((virFileReadPid(lxc_driver->stateDir, vm->def->name, &vm->pid)) != 0) {
VIR_FORCE_CLOSE(priv->monitor);
goto cleanup;
}
if (vm->pid != 0) {
vm->def->id = vm->pid;
virDomainObjSetState(vm, VIR_DOMAIN_RUNNING,
VIR_DOMAIN_RUNNING_UNKNOWN);
if ((priv->monitor = lxcMonitorClient(driver, vm)) < 0)
goto error;
if ((priv->monitorWatch = virEventAddHandle(
priv->monitor,
VIR_EVENT_HANDLE_ERROR | VIR_EVENT_HANDLE_HANGUP,
lxcMonitorEvent,
vm, NULL)) < 0) {
lxcVmTerminate(driver, vm, VIR_DOMAIN_SHUTOFF_FAILED);
virDomainAuditStop(vm, "failed");
goto cleanup;
}
vm, NULL)) < 0)
goto error;
} else {
vm->def->id = -1;
VIR_FORCE_CLOSE(priv->monitor);
@ -2082,6 +2078,12 @@ lxcReconnectVM(void *payload, const void *name ATTRIBUTE_UNUSED, void *opaque)
cleanup:
virDomainObjUnlock(vm);
return;
error:
lxcVmTerminate(driver, vm, VIR_DOMAIN_SHUTOFF_FAILED);
virDomainAuditStop(vm, "failed");
goto cleanup;
}