The set up I have used is,
#Define the Resource and Partitioning#Create a Database with 6 Partitions using
the MasterSlave State Model
./helix-admin.sh --zkSvr ${zkSvr} --addResource ${CLUSTER} ${RESOURCE} 3
MasterSlave
#Let Helix Assign Partitions to Nodes
./helix-admin.sh --zkSvr ${zkSvr} --rebalance ${CLUSTER} ${RESOURCE} 3
The above command is creating resource in Semi auto mode by default.
Open Issues:1) how do I specify full auto mode using ./helix-admin.sh command?
I don't see mode parameter (may be am I missing something?)
2) Is there a way to specify delay for state transition using ./helix-admin.sh ?
3) I tried other combination of 6 partitions with 3 replicas. Initially Ideal
State and External view client looks same. but after some time node 8086
showing offline state for some partitions. But surprisingly I don't see any
logs in my state transitions model class from any transitions to offline. what
could be the issue on why call backs are missing?
json snippet from listResourceInfo
lrao-ltm:bin lrao$ ./helix-admin.sh --zkSvr localhost:2181 --listResourceInfo
C1 R1
IdealState for R1:
{
"id" : "R1",
"mapFields" : {
"R1_0" : {
"localhost_8085" : "SLAVE",
"localhost_8086" : "MASTER",
"localhost_8087" : "SLAVE"
},
"R1_1" : {
"localhost_8085" : "SLAVE",
"localhost_8086" : "SLAVE",
"localhost_8087" : "MASTER"
},
"R1_2" : {
"localhost_8085" : "MASTER",
"localhost_8086" : "SLAVE",
"localhost_8087" : "SLAVE"
},
"R1_3" : {
"localhost_8085" : "SLAVE",
"localhost_8086" : "SLAVE",
"localhost_8087" : "MASTER"
},
"R1_4" : {
"localhost_8085" : "MASTER",
"localhost_8086" : "SLAVE",
"localhost_8087" : "SLAVE"
},
"R1_5" : {
"localhost_8085" : "SLAVE",
"localhost_8086" : "MASTER",
"localhost_8087" : "SLAVE"
}
},
"listFields" : {
"R1_0" : [ "localhost_8086", "localhost_8085", "localhost_8087" ],
"R1_1" : [ "localhost_8087", "localhost_8085", "localhost_8086" ],
"R1_2" : [ "localhost_8085", "localhost_8087", "localhost_8086" ],
"R1_3" : [ "localhost_8087", "localhost_8086", "localhost_8085" ],
"R1_4" : [ "localhost_8085", "localhost_8087", "localhost_8086" ],
"R1_5" : [ "localhost_8086", "localhost_8087", "localhost_8085" ]
},
"simpleFields" : {
"IDEAL_STATE_MODE" : "AUTO",
"NUM_PARTITIONS" : "6",
"REBALANCE_MODE" : "SEMI_AUTO",
"REBALANCE_STRATEGY" : "DEFAULT",
"REPLICAS" : "3",
"STATE_MODEL_DEF_REF" : "MasterSlave",
"STATE_MODEL_FACTORY_NAME" : "DEFAULT"
}
}
ExternalView for R1:
{
"id" : "R1",
"mapFields" : {
"R1_0" : {
"localhost_8085" : "SLAVE",
"localhost_8086" : "OFFLINE",
"localhost_8087" : "SLAVE"
},
"R1_1" : {
"localhost_8085" : "SLAVE",
"localhost_8086" : "SLAVE",
"localhost_8087" : "MASTER"
},
"R1_2" : {
"localhost_8085" : "SLAVE",
"localhost_8086" : "OFFLINE",
"localhost_8087" : "SLAVE"
},
"R1_3" : {
"localhost_8085" : "SLAVE",
"localhost_8086" : "SLAVE",
"localhost_8087" : "MASTER"
},
"R1_4" : {
"localhost_8085" : "SLAVE",
"localhost_8086" : "OFFLINE",
"localhost_8087" : "SLAVE"
},
"R1_5" : {
"localhost_8085" : "SLAVE",
"localhost_8086" : "SLAVE",
"localhost_8087" : "MASTER"
}
},
"listFields" : {
},
"simpleFields" : {
"BUCKET_SIZE" : "0",
"IDEAL_STATE_MODE" : "AUTO",
"NUM_PARTITIONS" : "6",
"REBALANCE_MODE" : "SEMI_AUTO",
"REBALANCE_STRATEGY" : "DEFAULT",
"REPLICAS" : "3",
"STATE_MODEL_DEF_REF" : "MasterSlave",
"STATE_MODEL_FACTORY_NAME" : "DEFAULT"
}
}
My participant class code:
public class HelixParticipant {
String clusterName;
String instanceName;
String zkConnectString;
SconeVagabondHandler stuff;
public HelixParticipant(String clusterName, String instanceName, String
zkConnectString, SconeVagabondHandler stuff) {
super();
this.clusterName = clusterName;
this.instanceName = instanceName;
this.zkConnectString = zkConnectString;
this.stuff = stuff;
}
public void start() {
try {
HelixManager manager = HelixManagerFactory.getZKHelixManager(clusterName,
instanceName,
InstanceType.PARTICIPANT, zkConnectString);
StateMachineEngine stateMach = manager.getStateMachineEngine();
RoutingTableProvider routingTableProvider = new RoutingTableProvider();
MasterSlaveStateModelFactory stateModelFactory = new
MasterSlaveStateModelFactory(stuff,routingTableProvider);
stateMach.registerStateModelFactory("MasterSlave", stateModelFactory);
manager.connect();
manager.addExternalViewChangeListener(routingTableProvider);
} catch (Exception ex) {
logger.log(Level.SEVERE, "Error during Participant start", ex);
}
}
}
Master slave model:
public class MasterSlaveStateModelFactory
extends StateModelFactory<StateModel> {
SconeVagabondHandler stuff;
RoutingTableProvider routingTableProvider;
public MasterSlaveStateModelFactory(SconeVagabondHandler stuff,
RoutingTableProvider routingTableProvider) {
this.stuff = stuff;
this.routingTableProvider = routingTableProvider;
}
@Override
public StateModel createNewStateModel(String resourceName, String
stateUnitKey) {
logger.info(
"MasterSlaveStateModelFactory => " + "resourceName " + resourceName + "
stateUnitKey " + stateUnitKey);
return new MasterSlaveStateModel(stateUnitKey, stuff, routingTableProvider);
}
@StateModelInfo(initialState = "OFFLINE", states =
"{'OFFLINE','SLAVE','MASTER', 'DROPPED'}")
public static class MasterSlaveStateModel extends StateModel {
private final String _stateUnitKey;
SconeHandler stuff;
RoutingTableProvider routingTableProvider;
public MasterSlaveStateModel(String stateUnitKey, SconeHandler
stuff,RoutingTableProvider routingTableProvider) {
_stateUnitKey = stateUnitKey;
this.stuff = stuff;
this.routingTableProvider = routingTableProvider;
}
@Transition(from = "MASTER", to = "SLAVE")
public void masterToSlave(Message message, NotificationContext context) {
logger.info("BootstrapProcess.BootstrapStateModel.masterToSlave()");
}
@Transition(from = "OFFLINE", to = "SLAVE")
public void offlineToSlave(Message message, NotificationContext context) {
logger.info("BootstrapProcess.BootstrapStateModel.offlineToSlave()");
}
@Transition(from = "SLAVE", to = "OFFLINE")
public void slaveToOffline(Message message, NotificationContext context) {
logger.info("BootstrapProcess.BootstrapStateModel.slaveToOffline()");
}
@Transition(from = "SLAVE", to = "MASTER")
public void slaveToMaster(Message message, NotificationContext context) {
logger.info("BootstrapProcess.BootstrapStateModel.slaveToMaster()");
}
@Transition(from = "OFFLINE", to = "DROPPED")
public void onBecomeDroppedFromOffline(Message message, NotificationContext
context) {
logger.info("BootstrapProcess.BootstrapStateModel.offlineToDropped()");
}
}
}
Controller class:
public class HelixController {
String clusterName;
String instanceName;
String zkConnectString;
public HelixController(String clusterName, String instanceName, String
zkConnectString) {
super();
this.clusterName = clusterName;
this.instanceName = instanceName;
this.zkConnectString = zkConnectString;
}
public void start(){
try{
HelixManager manager = HelixManagerFactory.getZKHelixManager(clusterName,
instanceName,
InstanceType.CONTROLLER,
zkConnectString);
manager.connect();
GenericHelixController controller = new GenericHelixController();
manager.addConfigChangeListener(controller);
manager.addLiveInstanceChangeListener(controller);
manager.addIdealStateChangeListener(controller);
//manager..addExternalViewChangeListener(controller);
manager.addControllerListener(controller);
}catch(Exception ex){
logger.log(Level.SEVERE, "Error during Controller start", ex);
}
}
}
do you see any issues with my above classes?
On Saturday, November 4, 2017, 6:13:46 AM GMT+5:30, Xue Junkai
<[email protected]> wrote:
Hi Leela,
Are your resources all in SemiAuto mode? SemiAuto mode assignment is based
on your preference list in your IdealState list fields. If you want to
spread it out, you have to change your preference list node order for
different partitions.
If you are using FullAuto mode, you will not have this problem.
best,
Junkai
On Fri, Nov 3, 2017 at 5:35 PM, leela maheswararao <
[email protected]> wrote:
> Team,In my example(SEMI_AUTO), I have configured 3 partitions with 3
> replicas on 3 nodes. Once all nodes are started, external view shows as
> below. Here all MASTER's are assigned to same node. Is there a way to
> spread MASTER's evenly? is this behavior due to server booting order?
>
> IdealState for R1:
>
> {
>
> "id" : "R1",
>
> "mapFields" : {
>
> "R1_0" : {
>
> "localhost_8085" : "MASTER",
>
> "localhost_8086" : "SLAVE",
>
> "localhost_8087" : "SLAVE"
>
> },
>
> "R1_1" : {
>
> "localhost_8085" : "SLAVE",
>
> "localhost_8086" : "SLAVE",
>
> "localhost_8087" : "MASTER"
>
> },
>
> "R1_2" : {
>
> "localhost_8085" : "SLAVE",
>
> "localhost_8086" : "MASTER",
>
> "localhost_8087" : "SLAVE"
>
> }
>
> },
>
> "listFields" : {
>
> "R1_0" : [ "localhost_8085", "localhost_8086", "localhost_8087" ],
>
> "R1_1" : [ "localhost_8087", "localhost_8085", "localhost_8086" ],
>
> "R1_2" : [ "localhost_8086", "localhost_8085", "localhost_8087" ]
>
> },
>
> "simpleFields" : {
>
> "IDEAL_STATE_MODE" : "AUTO",
>
> "NUM_PARTITIONS" : "3",
>
> "REBALANCE_MODE" : "SEMI_AUTO",
>
> "REBALANCE_STRATEGY" : "DEFAULT",
>
> "REPLICAS" : "3",
>
> "STATE_MODEL_DEF_REF" : "MasterSlave",
>
> "STATE_MODEL_FACTORY_NAME" : "DEFAULT"
>
> }
>
> }
>
>
>
>
> ExternalView for R1:
>
> {
>
> "id" : "R1",
>
> "mapFields" : {
>
> "R1_0" : {
>
> "localhost_8085" : "SLAVE",
>
> "localhost_8086" : "MASTER",
>
> "localhost_8087" : "SLAVE"
>
> },
>
> "R1_1" : {
>
> "localhost_8085" : "SLAVE",
>
> "localhost_8086" : "MASTER",
>
> "localhost_8087" : "SLAVE"
>
> },
>
> "R1_2" : {
>
> "localhost_8085" : "SLAVE",
>
> "localhost_8086" : "MASTER",
>
> "localhost_8087" : "SLAVE"
>
> }
>
> },
>
> "listFields" : {
>
> },
>
> "simpleFields" : {
>
> "BUCKET_SIZE" : "0",
>
> "IDEAL_STATE_MODE" : "AUTO",
>
> "NUM_PARTITIONS" : "3",
>
> "REBALANCE_MODE" : "SEMI_AUTO",
>
> "REBALANCE_STRATEGY" : "DEFAULT",
>
> "REPLICAS" : "3",
>
> "STATE_MODEL_DEF_REF" : "MasterSlave",
>
> "STATE_MODEL_FACTORY_NAME" : "DEFAULT"
>
> }
>
> }
> Regards,Mahesh
>
