andrijapanicsb commented on a change in pull request #3575: [WIP DO NOT MERGE] 
Health check feature for virtual router
URL: https://github.com/apache/cloudstack/pull/3575#discussion_r368638544
 
 

 ##########
 File path: 
server/src/main/java/com/cloud/network/router/VirtualNetworkApplianceManagerImpl.java
 ##########
 @@ -1186,6 +1238,586 @@ protected void pushToUpdateQueue(final List<NetworkVO> 
networks) throws Interrup
         }
     }
 
+    protected class FetchRouterHealthChecksResultTask extends 
ManagedContextRunnable {
+        public FetchRouterHealthChecksResultTask() {
+        }
+
+        @Override
+        protected void runInContext() {
+            try {
+                final List<DomainRouterVO> routers = 
_routerDao.listByStateAndManagementServer(VirtualMachine.State.Running, 
mgmtSrvrId);
+                s_logger.info("Found " + routers.size() + " running routers. 
Fetching, analysing and updating DB for the health checks.");
+                if (!RouterHealthChecksEnabled.value()) {
+                    s_logger.debug("Skipping fetching of router health check 
results as router.health.checks.enabled is disabled");
+                    return;
+                }
+
+                for (final DomainRouterVO router : routers) {
+                    GetRouterMonitorResultsAnswer answer = 
fetchAndUpdateRouterHealthChecks(router, false);
+                    List<String> failingChecks = getFailingChecks(router, 
answer);
+                    handleFailingChecks(router, failingChecks);
+                }
+            } catch (final Exception ex) {
+                s_logger.error("Fail to complete the 
FetchRouterHealthChecksResultTask! ", ex);
+                ex.printStackTrace();
+            }
+        }
+
+        private List<String> getFailingChecks(DomainRouterVO router, 
GetRouterMonitorResultsAnswer answer) {
+            if (answer == null) {
+                s_logger.warn("Unable to fetch monitor results for router " + 
router);
+                updateRouterConnectivityHealthCheck(router.getId(), false, 
"Communication failed");
+                return Arrays.asList(CONNECTIVITY_TEST);
+            } else if (!answer.getResult()) {
+                s_logger.warn("Failed to fetch monitor results from router " + 
router + " with details: " + answer.getDetails());
+                updateRouterConnectivityHealthCheck(router.getId(), false, 
"Failed to fetch results with details: " + answer.getDetails());
+                return Arrays.asList(CONNECTIVITY_TEST);
+            } else {
+                updateRouterConnectivityHealthCheck(router.getId(), true, 
"Successfully fetched data");
+                updateDbHealthChecksFromRouterResponse(router.getId(), 
answer.getMonitoringResults());
+                return answer.getFailingChecks();
+            }
+        }
+
+        private void handleFailingChecks(DomainRouterVO router, List<String> 
failingChecks) {
+            if (failingChecks == null || failingChecks.size() == 0) {
+                return;
+            }
+
+            String alertMessage = "Health checks failed: " + 
failingChecks.size() + " failing checks on router " + router.getUuid();
+            _alertMgr.sendAlert(AlertType.ALERT_TYPE_DOMAIN_ROUTER, 
router.getDataCenterId(), router.getPodIdToDeployIn(),
+                    alertMessage, alertMessage);
+            s_logger.warn(alertMessage + ". Checking failed health checks to 
see if router needs reboot");
 
 Review comment:
   Not sure it's done? 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to 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

Reply via email to