Search in sources :

Example 1 with ConsistencyController

use of com.tencent.angel.psagent.consistency.ConsistencyController in project angel by Tencent.

the class PSAgent method initAndStart.

public void initAndStart() throws Exception {
    // Get ps locations from master and put them to the location cache.
    locationManager = new PSAgentLocationManager(PSAgentContext.get());
    locationManager.setMasterLocation(masterLocation);
    // Build and initialize rpc client to master
    masterClient = new MasterClient();
    masterClient.init();
    // Build local location
    String localIp = NetUtils.getRealLocalIP();
    int port = NetUtils.chooseAListenPort(conf);
    location = new Location(localIp, port);
    // Initialize matrix meta information
    clockCache = new ClockCache();
    List<MatrixMeta> matrixMetas = masterClient.getMatrices();
    LOG.info("===========================PSAgent get matrices from master," + matrixMetas.size());
    this.matrixMetaManager = new PSAgentMatrixMetaManager(clockCache);
    matrixMetaManager.addMatrices(matrixMetas);
    Map<ParameterServerId, Location> psIdToLocMap = masterClient.getPSLocations();
    List<ParameterServerId> psIds = new ArrayList<>(psIdToLocMap.keySet());
    Collections.sort(psIds, new Comparator<ParameterServerId>() {

        @Override
        public int compare(ParameterServerId s1, ParameterServerId s2) {
            return s1.getIndex() - s2.getIndex();
        }
    });
    int size = psIds.size();
    locationManager.setPsIds(psIds.toArray(new ParameterServerId[0]));
    for (int i = 0; i < size; i++) {
        if (psIdToLocMap.containsKey(psIds.get(i))) {
            locationManager.setPsLocation(psIds.get(i), psIdToLocMap.get(psIds.get(i)));
        }
    }
    matrixTransClient = new MatrixTransportClient();
    matrixClientAdapter = new MatrixClientAdapter();
    opLogCache = new MatrixOpLogCache();
    matrixStorageManager = new MatrixStorageManager();
    matricesCache = new MatricesCache();
    int staleness = conf.getInt(AngelConf.ANGEL_STALENESS, AngelConf.DEFAULT_ANGEL_STALENESS);
    consistencyController = new ConsistencyController(staleness);
    consistencyController.init();
    psAgentInitFinishedFlag.set(true);
    // Start heartbeat thread if need
    if (needHeartBeat) {
        startHeartbeatThread();
    }
    // Start all services
    matrixTransClient.start();
    matrixClientAdapter.start();
    clockCache.start();
    opLogCache.start();
    matricesCache.start();
}
Also used : MatrixClientAdapter(com.tencent.angel.psagent.matrix.transport.adapter.MatrixClientAdapter) ClockCache(com.tencent.angel.psagent.clock.ClockCache) MasterClient(com.tencent.angel.psagent.client.MasterClient) MatrixMeta(com.tencent.angel.ml.matrix.MatrixMeta) PSAgentMatrixMetaManager(com.tencent.angel.psagent.matrix.PSAgentMatrixMetaManager) MatricesCache(com.tencent.angel.psagent.matrix.cache.MatricesCache) ConsistencyController(com.tencent.angel.psagent.consistency.ConsistencyController) MatrixTransportClient(com.tencent.angel.psagent.matrix.transport.MatrixTransportClient) MatrixOpLogCache(com.tencent.angel.psagent.matrix.oplog.cache.MatrixOpLogCache) PSAgentLocationManager(com.tencent.angel.psagent.matrix.PSAgentLocationManager) MatrixStorageManager(com.tencent.angel.psagent.matrix.storage.MatrixStorageManager) ParameterServerId(com.tencent.angel.ps.ParameterServerId) Location(com.tencent.angel.common.location.Location)

Example 2 with ConsistencyController

use of com.tencent.angel.psagent.consistency.ConsistencyController in project angel by Tencent.

the class PSAgentTest method testConsistencyController.

@Test
public void testConsistencyController() throws Exception {
    try {
        AngelApplicationMaster angelAppMaster = LocalClusterContext.get().getMaster().getAppMaster();
        assertTrue(angelAppMaster != null);
        AMTaskManager taskManager = angelAppMaster.getAppContext().getTaskManager();
        assertTrue(taskManager != null);
        WorkerManager workerManager = angelAppMaster.getAppContext().getWorkerManager();
        assertTrue(workerManager != null);
        Worker worker = LocalClusterContext.get().getWorker(worker0Attempt0Id).getWorker();
        assertTrue(worker != null);
        PSAgent psAgent = worker.getPSAgent();
        assertTrue(psAgent != null);
        ConsistencyController consistControl = psAgent.getConsistencyController();
        assertTrue(consistControl != null);
        PSAgentContext psAgentContext = PSAgentContext.get();
        assertTrue(psAgentContext.getPsAgent() != null);
        TaskContext taskContext1 = psAgentContext.getTaskContext(1);
        TaskContext taskContext2 = psAgentContext.getTaskContext(2);
        assertTrue(taskContext1 != null);
        assertTrue(taskContext2 != null);
        int matrix1Id = LocalClusterContext.get().getMaster().getAppMaster().getAppContext().getMatrixMetaManager().getMatrix("w1").getId();
        int matrix2Id = LocalClusterContext.get().getMaster().getAppMaster().getAppContext().getMatrixMetaManager().getMatrix("w2").getId();
        TVector row1 = consistControl.getRow(taskContext1, matrix1Id, 0);
        assertTrue(row1 != null);
        assertEquals(row1.size(), 100000);
        TVector row2 = consistControl.getRow(taskContext1, matrix2Id, 0);
        assertTrue(row2 != null);
        assertEquals(row2.size(), 100000);
        consistControl.clock(taskContext1, matrix1Id, true);
        assertEquals(taskContext1.getMatrixClock(matrix1Id), 1);
        int staleness = psAgent.getConf().getInt(AngelConf.ANGEL_STALENESS, AngelConf.DEFAULT_ANGEL_STALENESS);
    } catch (Exception x) {
        LOG.error("run testConsistencyController failed ", x);
        throw x;
    }
}
Also used : WorkerManager(com.tencent.angel.master.worker.WorkerManager) AMTaskManager(com.tencent.angel.master.task.AMTaskManager) TaskContext(com.tencent.angel.psagent.task.TaskContext) AngelApplicationMaster(com.tencent.angel.master.AngelApplicationMaster) Worker(com.tencent.angel.worker.Worker) TVector(com.tencent.angel.ml.math.TVector) ConsistencyController(com.tencent.angel.psagent.consistency.ConsistencyController) Test(org.junit.Test)

Aggregations

ConsistencyController (com.tencent.angel.psagent.consistency.ConsistencyController)2 Location (com.tencent.angel.common.location.Location)1 AngelApplicationMaster (com.tencent.angel.master.AngelApplicationMaster)1 AMTaskManager (com.tencent.angel.master.task.AMTaskManager)1 WorkerManager (com.tencent.angel.master.worker.WorkerManager)1 TVector (com.tencent.angel.ml.math.TVector)1 MatrixMeta (com.tencent.angel.ml.matrix.MatrixMeta)1 ParameterServerId (com.tencent.angel.ps.ParameterServerId)1 MasterClient (com.tencent.angel.psagent.client.MasterClient)1 ClockCache (com.tencent.angel.psagent.clock.ClockCache)1 PSAgentLocationManager (com.tencent.angel.psagent.matrix.PSAgentLocationManager)1 PSAgentMatrixMetaManager (com.tencent.angel.psagent.matrix.PSAgentMatrixMetaManager)1 MatricesCache (com.tencent.angel.psagent.matrix.cache.MatricesCache)1 MatrixOpLogCache (com.tencent.angel.psagent.matrix.oplog.cache.MatrixOpLogCache)1 MatrixStorageManager (com.tencent.angel.psagent.matrix.storage.MatrixStorageManager)1 MatrixTransportClient (com.tencent.angel.psagent.matrix.transport.MatrixTransportClient)1 MatrixClientAdapter (com.tencent.angel.psagent.matrix.transport.adapter.MatrixClientAdapter)1 TaskContext (com.tencent.angel.psagent.task.TaskContext)1 Worker (com.tencent.angel.worker.Worker)1 Test (org.junit.Test)1