DaanHoogland commented on a change in pull request #2474: CLOUDSTACK-10246 Fix
Host HA and VM HA issues
URL: https://github.com/apache/cloudstack/pull/2474#discussion_r171784133
##########
File path:
engine/orchestration/src/com/cloud/agent/manager/AgentManagerImpl.java
##########
@@ -843,72 +846,103 @@ protected boolean
handleDisconnectWithInvestigation(final AgentAttache attache,
s_logger.debug("Caught exception while getting agent's next
status", ne);
}
+ // For log and alert purposes later
+ final DataCenterVO dcVO = _dcDao.findById(host.getDataCenterId());
+ final HostPodVO podVO = _podDao.findById(host.getPodId());
+ final String hostDesc = "[name: " + host.getName() + " (id:" +
host.getId() + "), availability zone: " + dcVO.getName() + ", pod: " +
podVO.getName() + "]";
+ final String hostShortDesc = "Host " + host.getName() + " (id:" +
host.getId() + ")";
+
+ final ResourceState resourceState = host.getResourceState();
+ if (resourceState == ResourceState.Disabled || resourceState ==
ResourceState.Maintenance || resourceState == ResourceState.ErrorInMaintenance)
{
+ // If we are in this resourceState, no need to investigate or
do anything. AgentMonitor will handle when in these resourceStates
+ s_logger.info(hostShortDesc + " has disconnected with event "
+ event + ", but is in Resource State of " + resourceState + ", so doing
nothing");
+ return true;
+ }
+
if (nextStatus == Status.Alert) {
- /* OK, we are going to the bad status, let's see what happened
*/
- s_logger.info("Investigating why host " + hostId + " has
disconnected with event " + event);
+ /* Our next Agent transition state is Alert
+ * Let's see if the host down or why we had this event
+ */
+ s_logger.info("Investigating why host " + hostShortDesc + "
has disconnected with event " + event);
Status determinedState = investigate(attache);
// if state cannot be determined do nothing and bail out
if (determinedState == null) {
if ((System.currentTimeMillis() >> 10) -
host.getLastPinged() > AlertWait.value()) {
- s_logger.warn("Agent " + hostId + " state cannot be
determined for more than " + AlertWait + "(" + AlertWait.value() + ") seconds,
will go to Alert state");
+ s_logger.warn("State for " + hostShortDesc + " could
not be determined for more than " + AlertWait + "(" + AlertWait.value() + ")
seconds, will go to Alert state");
Review comment:
for warn message the above is even more true
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
