[
https://issues.apache.org/jira/browse/CLOUDSTACK-10246?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16383332#comment-16383332
]
ASF GitHub Bot commented on CLOUDSTACK-10246:
---------------------------------------------
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_r171784702
##########
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");
determinedState = Status.Alert;
} else {
- s_logger.warn("Agent " + hostId + " state cannot be
determined, do nothing");
+ s_logger.warn("State for " + hostShortDesc + " could
not be determined, doing nothing");
return false;
}
}
final Status currentStatus = host.getStatus();
- s_logger.info("The agent from host " + hostId + " state
determined is " + determinedState);
+ s_logger.info("Status for " + hostShortDesc + " was " +
currentStatus + ". Investigation determined the current state is " +
determinedState);
- if (determinedState == Status.Down) {
- final String message = "Host is down: " + host.getId() +
"-" + host.getName() + ". Starting HA on the VMs";
- s_logger.error(message);
- if (host.getType() != Host.Type.SecondaryStorage &&
host.getType() != Host.Type.ConsoleProxy) {
-
_alertMgr.sendAlert(AlertManager.AlertType.ALERT_TYPE_HOST,
host.getDataCenterId(), host.getPodId(), "Host down, " + host.getId(), message);
- }
- event = Status.Event.HostDown;
- } else if (determinedState == Status.Up) {
- /* Got ping response from host, bring it back */
- s_logger.info("Agent is determined to be up and running");
+ if (determinedState == Status.Up) {
+ // Got ping response from host, bring it back
+ s_logger.info(hostShortDesc + " is up again");
agentStatusTransitTo(host, Status.Event.Ping, _nodeId);
- return false;
} else if (determinedState == Status.Disconnected) {
- s_logger.warn("Agent is disconnected but the host is still
up: " + host.getId() + "-" + host.getName());
+ // Investigation says host isn't down, just disconnected
if (currentStatus == Status.Disconnected) {
+ // Last status was disconnected, only switch status if
AlertWait has passed
if ((System.currentTimeMillis() >> 10) -
host.getLastPinged() > AlertWait.value()) {
- s_logger.warn("Host " + host.getId() + " has been
disconnected past the wait time it should be disconnected.");
- event = Status.Event.WaitedTooLong;
+ s_logger.error("The agent on " + hostShortDesc
+ " has been disconnected longer than " + AlertWait + " (" + AlertWait.value()
+ " seconds). Setting event to WaitedTooLong");
+ if (host.getType() !=
Host.Type.SecondaryStorage && host.getType() != Host.Type.ConsoleProxy) {
+
_alertMgr.sendAlert(AlertManager.AlertType.ALERT_TYPE_HOST,
host.getDataCenterId(), host.getPodId(), hostShortDesc + " is in Alert status",
+ "The agent for host " +
hostDesc + " has been disconnected longer than " + AlertWait + " (" +
AlertWait.value() + " seconds), host will be put into Alert status.");
+ }
+ event = Status.Event.WaitedTooLong; // Will
put into Alert status at transition
} else {
- s_logger.debug("Host " + host.getId() + " has been
determined to be disconnected but it hasn't passed the wait time yet.");
+ // Host hasn't been disconnected long enough to
change status to Alert
+ s_logger.warn(hostShortDesc + " has been
disconnected for " + ((System.currentTimeMillis() >> 10) -
host.getLastPinged()) + " seconds, but for less than " + AlertWait + " (" +
AlertWait.value() + " seconds). No action taken.");
return false;
}
} else if (currentStatus == Status.Up) {
- 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();
- if (host.getType() != Host.Type.SecondaryStorage &&
host.getType() != Host.Type.ConsoleProxy) {
-
_alertMgr.sendAlert(AlertManager.AlertType.ALERT_TYPE_HOST,
host.getDataCenterId(), host.getPodId(), "Host disconnected, " + hostDesc,
- "If the agent for host [" +
hostDesc + "] is not restarted within " + AlertWait + " seconds, host will go
to Alert state");
- }
- event = Status.Event.AgentDisconnected;
+ // Host was up, but now agent is disconnected
+ // If host stays disconnected, it will be handled
again next time it is investigated
+ s_logger.warn(hostShortDesc + " was up but is now
disconnected. Setting event to AgentUnreachable.");
+ event = Status.Event.AgentUnreachable; // Will put
into Disconnected status at transition
+
_alertMgr.sendAlert(AlertManager.AlertType.ALERT_TYPE_HOST,
host.getDataCenterId(), host.getPodId(), hostShortDesc + " is " +
determinedState,
+ "The host " + hostDesc + " was " +
currentStatus + ", but has now the host agent is in " + Status.Disconnected +
". If the host is disconnected longer than " + AlertWait + " (" +
AlertWait.value() + " seconds), it will be put into Alert status.");
+ } else if (currentStatus == Status.Alert) {
+ s_logger.error(hostShortDesc + " was in and is still
in " + Status.Alert + ". No action taken.");
+ return false;
+ }
+ else {
+ // If we are here, host was in another status, but
next status is alert so let's alert
+ s_logger.error(hostShortDesc + " was in " +
currentStatus + ", and investigation determined it is " + Status.Disconnected);
+
_alertMgr.sendAlert(AlertManager.AlertType.ALERT_TYPE_HOST,
host.getDataCenterId(), host.getPodId(), hostShortDesc + " is " +
determinedState, "The host " + hostDesc + " was in " + currentStatus + ", and
investigation determined it is " + Status.Disconnected);
}
+ } else if (determinedState == Status.Down) {
+ // Host was determined down - not just disconnected
+ s_logger.error(hostShortDesc + " is down. Setting event
to HostDown and will start HA on the VMs");
+ if (host.getType() != Host.Type.SecondaryStorage &&
host.getType() != Host.Type.ConsoleProxy) {
+
_alertMgr.sendAlert(AlertManager.AlertType.ALERT_TYPE_HOST,
host.getDataCenterId(), host.getPodId(), hostShortDesc + " is down", "Host " +
hostDesc + " is down. Will start HA on the VMs");
+ }
+ else {
+
_alertMgr.sendAlert(AlertManager.AlertType.ALERT_TYPE_HOST,
host.getDataCenterId(), host.getPodId(), hostShortDesc + " is down", "Host " +
hostDesc + " is down.");
+ }
+ event = Status.Event.HostDown;
+ removeAgent = true;
+ } else if (determinedState == Status.Alert){
+ // This is likely a Console Proxy or Secondary Storage VM
+ s_logger.error("Investigation found " + hostShortDesc + "
in state: " + determinedState);
+
_alertMgr.sendAlert(AlertManager.AlertType.ALERT_TYPE_HOST,
host.getDataCenterId(), host.getPodId(), "Investigation found " + hostShortDesc
+ " in " + determinedState, "Investigation found " + hostShortDesc + " in " +
determinedState + " state. Event is " + event);
} else {
- // if we end up here we are in alert state, send an alert
- final DataCenterVO dcVO =
_dcDao.findById(host.getDataCenterId());
- final HostPodVO podVO = _podDao.findById(host.getPodId());
- final String podName = podVO != null ? podVO.getName() :
"NO POD";
- final String hostDesc = "name: " + host.getName() + "
(id:" + host.getId() + "), availability zone: " + dcVO.getName() + ", pod: " +
podName;
-
_alertMgr.sendAlert(AlertManager.AlertType.ALERT_TYPE_HOST,
host.getDataCenterId(), host.getPodId(), "Host in ALERT state, " + hostDesc,
- "In availability zone " +
host.getDataCenterId() + ", host is in alert state: " + host.getId() + "-" +
host.getName());
+ // Determined state was not Up, Disconnected, Down, or
Alert. To catch anything else create alert
+ s_logger.error("Investigation found " + hostShortDesc + "
in unhandled state: " + determinedState);
+
_alertMgr.sendAlert(AlertManager.AlertType.ALERT_TYPE_HOST,
host.getDataCenterId(), host.getPodId(), "Investigation found " + hostShortDesc
+ " in " + determinedState, "Investigation found " + hostShortDesc + " in
unhandled state: " + determinedState);
}
} else {
- s_logger.debug("The next status of agent " + host.getId() + "
is not Alert, no need to investigate what happened");
+ s_logger.info("The next status of host " + hostShortDesc + "
is " + nextStatus + ", no need to investigate what happened");
}
}
- handleDisconnectWithoutInvestigation(attache, event, true, true);
- host = _hostDao.findById(hostId); // Maybe the host magically
reappeared?
+
+ handleDisconnectWithoutInvestigation(attache, event, true,
removeAgent);
+ host = _hostDao.findById(hostId); // We may have transitioned the
status - refresh
Review comment:
protected boolean handleDisconnectWithInvestigation(final AgentAttache
attache, Status.Event event) just grew from 85 to 118 lines. Can you please
make it a bit more modular?
----------------------------------------------------------------
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:
us...@infra.apache.org
> VM HA issues
> ------------
>
> Key: CLOUDSTACK-10246
> URL: https://issues.apache.org/jira/browse/CLOUDSTACK-10246
> Project: CloudStack
> Issue Type: Bug
> Security Level: Public(Anyone can view this level - this is the
> default.)
> Components: Management Server
> Affects Versions: 4.11.0.0
> Environment: My setup is CentOS 7 Management server with 3 CentOS 7
> KVM HVs, NFS as primary and secondary storages.
> Reporter: Nux
> Priority: Major
>
> VM HA fails to kick in when one of the hypervisors goes down.
> It even fails to restart the system VMs which remain down along with the
> instances until the affected HV comes back online.
> When I crash or power off the HV the system marks it in the hosts list as
> "Alert" or "Disconnected" respectively. It should get changed to "Down" after
> that, but this never happens.
>
> I have tried various combinations of setups (Adv, Basic), none succeeded.
>
> My instances use HA enabled offerings.
> Management server DEBUG logs here:
> [http://tmp.nux.ro/CW4-vmhafail-411rc1.txt]
>
>
>
>
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
