Bug: HA takes a lot of time to migrate VMs (trigger HA) to another KVM

sudison · sudison · commit f497c7c031b5 · 2012-07-25T10:17:09.000-07:00
host if there are multiple storage pools in a cluster. The issue is as follows: 1. When CloudStack detects that a host is not responding to ping requests it'll send a fence command for this host to another host in the cluster. 2. The agent takes a long time to respond to this check if the storage is fenced. This is because the agent checks if the first host is writing to its heartbeat file on all pools in the cluster. It is doing this in a sequential manner on all storage pool. Making a fix to get rid of sleep, wait during HA. The behavior is now similar to Xenserver. RB: https://reviews.apache.org/r/6133/ Send-by:devdeep.singh@citrix.com
diff --git a/agent/src/com/cloud/agent/resource/computing/KVMHAChecker.java b/agent/src/com/cloud/agent/resource/computing/KVMHAChecker.java
@@ -53,7 +53,7 @@ private Boolean checkingHB() {
             cmd.add("-h", _hostIP);
             cmd.add("-r");
             cmd.add("-t",
-                    String.valueOf((_heartBeatUpdateFreq + _heartBeatUpdateTimeout) / 1000 * 2));
+                    String.valueOf(_heartBeatUpdateFreq/1000));
             OutputInterpreter.OneLineParser parser = new OutputInterpreter.OneLineParser();
             String result = cmd.execute(parser);
             s_logger.debug("pool: " + pool._poolIp);
diff --git a/scripts/vm/hypervisor/kvm/kvmheartbeat.sh b/scripts/vm/hypervisor/kvm/kvmheartbeat.sh
@@ -133,14 +133,14 @@ write_hbLog() {
 }
 
 check_hbLog() {
-  oldTimeStamp=$(cat $hbFile) 
-  sleep $interval &> /dev/null
-  newTimeStamp=$(cat $hbFile) 
-  if [ $newTimeStamp -gt $oldTimeStamp ]
+  now=$(date +%s)
+  hb=$(cat $hbFile)
+  diff=`expr $now - $hb`
+  if [ $diff -gt $interval ]
   then
-    return 0
+    return 1
   fi
-  return 1
+  return 0
 }
 
 if [ "$rflag" == "1" ]
