Examples with AMTaskManager com.tencent.angel.master.task.AMTaskManager used on opensource projects

Example 6 with AMTaskManager

use of com.tencent.angel.master.task.AMTaskManager in project angel by Tencent.

the class MatrixMetaManagerTest method testCreateMatrix.

@Test
public void testCreateMatrix() throws Exception {
    try {
        LOG.info("===========================testCreateMatrix===============================");
        Worker worker = LocalClusterContext.get().getWorker(worker0Attempt0Id).getWorker();
        MasterClient masterClient = worker.getPSAgent().getMasterClient();
        int w3Id = -1;
        int w4Id = -1;
        // add matrix
        MatrixContext mMatrix = new MatrixContext();
        mMatrix.setName("w3");
        mMatrix.setRowNum(1);
        mMatrix.setColNum(100000);
        mMatrix.setMaxRowNumInBlock(1);
        mMatrix.setMaxColNumInBlock(50000);
        mMatrix.setRowType(RowType.T_DOUBLE_DENSE);
        mMatrix.set(MatrixConf.MATRIX_OPLOG_ENABLEFILTER, "false");
        mMatrix.set(MatrixConf.MATRIX_HOGWILD, "true");
        mMatrix.set(MatrixConf.MATRIX_AVERAGE, "false");
        mMatrix.set(MatrixConf.MATRIX_OPLOG_TYPE, RowType.T_DOUBLE_DENSE.name());
        masterClient.createMatrix(mMatrix, 10000);
        mMatrix.setName("w4");
        mMatrix.setRowNum(1);
        mMatrix.setColNum(100000);
        mMatrix.setMaxRowNumInBlock(1);
        mMatrix.setMaxColNumInBlock(50000);
        mMatrix.setRowType(RowType.T_DOUBLE_DENSE);
        mMatrix.set(MatrixConf.MATRIX_OPLOG_ENABLEFILTER, "false");
        mMatrix.set(MatrixConf.MATRIX_HOGWILD, "true");
        mMatrix.set(MatrixConf.MATRIX_AVERAGE, "false");
        mMatrix.set(MatrixConf.MATRIX_OPLOG_TYPE, RowType.T_DOUBLE_DENSE.name());
        masterClient.createMatrix(mMatrix, 10000);
        MatrixMeta w3Meta = worker.getPSAgent().getMatrixMetaManager().getMatrixMeta("w3");
        MatrixMeta w4Meta = worker.getPSAgent().getMatrixMetaManager().getMatrixMeta("w4");
        assertEquals(w3Meta.getRowNum(), 1);
        assertEquals(w3Meta.getColNum(), 100000);
        assertEquals(w3Meta.getRowType(), RowType.T_DOUBLE_DENSE);
        assertEquals(w4Meta.getRowNum(), 1);
        assertEquals(w4Meta.getColNum(), 100000);
        assertEquals(w4Meta.getRowType(), RowType.T_DOUBLE_DENSE);
        w3Id = w3Meta.getId();
        w4Id = w4Meta.getId();
        AngelApplicationMaster angelAppMaster = LocalClusterContext.get().getMaster().getAppMaster();
        assertTrue(angelAppMaster != null);
        AMMatrixMetaManager matrixMetaManager = angelAppMaster.getAppContext().getMatrixMetaManager();
        MatrixMeta matrixw3Proto = matrixMetaManager.getMatrix("w3");
        MatrixMeta matrixw4Proto = matrixMetaManager.getMatrix("w4");
        assertNotNull(matrixw3Proto);
        assertNotNull(matrixw4Proto);
        assertEquals(matrixw3Proto.getRowNum(), 1);
        assertEquals(matrixw3Proto.getColNum(), 100000);
        assertEquals(matrixw3Proto.getPartitionMetas().size(), 2);
        Map<Integer, PartitionMeta> w3Parts = matrixw3Proto.getPartitionMetas();
        assertEquals(w3Parts.get(0).getPss().get(0), psId);
        assertEquals(w3Parts.get(0).getPartId(), 0);
        assertEquals(w3Parts.get(0).getStartRow(), 0);
        assertEquals(w3Parts.get(0).getEndRow(), 1);
        assertEquals(w3Parts.get(0).getStartCol(), 0);
        assertEquals(w3Parts.get(0).getEndCol(), 50000);
        assertEquals(w3Parts.get(1).getPartId(), 1);
        assertEquals(w3Parts.get(1).getStartRow(), 0);
        assertEquals(w3Parts.get(1).getEndRow(), 1);
        assertEquals(w3Parts.get(1).getStartCol(), 50000);
        assertEquals(w3Parts.get(1).getEndCol(), 100000);
        Map<Integer, PartitionMeta> w4Parts = matrixw4Proto.getPartitionMetas();
        assertEquals(w4Parts.get(0).getPss().get(0), psId);
        assertEquals(w4Parts.get(0).getPartId(), 0);
        assertEquals(w4Parts.get(0).getStartRow(), 0);
        assertEquals(w4Parts.get(0).getEndRow(), 1);
        assertEquals(w4Parts.get(0).getStartCol(), 0);
        assertEquals(w4Parts.get(0).getEndCol(), 50000);
        assertEquals(w4Parts.get(1).getPartId(), 1);
        assertEquals(w4Parts.get(1).getStartRow(), 0);
        assertEquals(w4Parts.get(1).getEndRow(), 1);
        assertEquals(w4Parts.get(1).getStartCol(), 50000);
        assertEquals(w4Parts.get(1).getEndCol(), 100000);
        ParameterServer ps = LocalClusterContext.get().getPS(psAttempt0Id).getPS();
        PSMatrixMetaManager matrixPartManager = ps.getMatrixMetaManager();
        PartitionMeta w3Part0 = matrixPartManager.getPartMeta(w3Id, 0);
        PartitionMeta w3Part1 = matrixPartManager.getPartMeta(w3Id, 1);
        assertTrue(w3Part0 != null);
        assertTrue(w3Part1 != null);
        assertEquals(w3Part0.getPartitionKey().getStartRow(), 0);
        assertEquals(w3Part0.getPartitionKey().getEndRow(), 1);
        assertEquals(w3Part0.getPartitionKey().getStartCol(), 0);
        assertEquals(w3Part0.getPartitionKey().getEndCol(), 50000);
        assertEquals(w3Part1.getPartitionKey().getStartRow(), 0);
        assertEquals(w3Part1.getPartitionKey().getEndRow(), 1);
        assertEquals(w3Part1.getPartitionKey().getStartCol(), 50000);
        assertEquals(w3Part1.getPartitionKey().getEndCol(), 100000);
        PartitionMeta w4Part0 = matrixPartManager.getPartMeta(w4Id, 0);
        PartitionMeta w4Part1 = matrixPartManager.getPartMeta(w4Id, 1);
        assertTrue(w4Part0 != null);
        assertTrue(w4Part1 != null);
        assertEquals(w4Part0.getPartitionKey().getStartRow(), 0);
        assertEquals(w4Part0.getPartitionKey().getEndRow(), 1);
        assertEquals(w4Part0.getPartitionKey().getStartCol(), 0);
        assertEquals(w4Part0.getPartitionKey().getEndCol(), 50000);
        assertEquals(w4Part1.getPartitionKey().getStartRow(), 0);
        assertEquals(w4Part1.getPartitionKey().getEndRow(), 1);
        assertEquals(w4Part1.getPartitionKey().getStartCol(), 50000);
        assertEquals(w4Part1.getPartitionKey().getEndCol(), 100000);
        MatrixClient w4ClientForTask0 = worker.getPSAgent().getMatrixClient("w4", 0);
        MatrixClient w4ClientForTask1 = worker.getPSAgent().getMatrixClient("w4", 1);
        TaskContext task0Context = w4ClientForTask0.getTaskContext();
        TaskContext task1Context = w4ClientForTask1.getTaskContext();
        double[] delta = new double[100000];
        for (int i = 0; i < delta.length; i++) {
            delta[i] = 1.0;
        }
        int iterIndex = 0;
        while (iterIndex < 5) {
            IntDoubleVector row1 = (IntDoubleVector) w4ClientForTask0.getRow(0);
            double sum1 = sum(row1.getStorage().getValues());
            LOG.info("taskid=" + task0Context.getIndex() + ", matrixId=" + w4ClientForTask0.getMatrixId() + ", rowIndex=0, local row sum=" + sum1);
            IntDoubleVector deltaRow1 = new IntDoubleVector(delta.length, new IntDoubleDenseVectorStorage(delta));
            deltaRow1.setMatrixId(w4ClientForTask0.getMatrixId());
            deltaRow1.setRowId(0);
            w4ClientForTask0.increment(deltaRow1);
            w4ClientForTask0.clock().get();
            task0Context.increaseEpoch();
            IntDoubleVector row2 = (IntDoubleVector) w4ClientForTask1.getRow(0);
            double sum2 = sum(row2.getStorage().getValues());
            LOG.info("taskid=" + task1Context.getIndex() + ", matrixId=" + w4ClientForTask1.getMatrixId() + ", rowIndex=1, local row sum=" + sum2);
            IntDoubleVector deltaRow2 = new IntDoubleVector(delta.length, new IntDoubleDenseVectorStorage(delta));
            deltaRow2.setMatrixId(w4ClientForTask1.getMatrixId());
            deltaRow2.setRowId(0);
            w4ClientForTask1.increment(deltaRow2);
            w4ClientForTask1.clock().get();
            task1Context.increaseEpoch();
            iterIndex++;
        }
        AMTaskManager amTaskManager = angelAppMaster.getAppContext().getTaskManager();
        AMTask amTask0 = amTaskManager.getTask(task0Id);
        AMTask amTask1 = amTaskManager.getTask(task1Id);
        assertEquals(amTask0.getIteration(), 5);
        assertEquals(amTask1.getIteration(), 5);
        Int2IntOpenHashMap task0MatrixClocks = amTask0.getMatrixClocks();
        assertEquals(task0MatrixClocks.size(), 1);
        assertEquals(task0MatrixClocks.get(w4Id), 5);
        Int2IntOpenHashMap task1MatrixClocks = amTask1.getMatrixClocks();
        assertEquals(task1MatrixClocks.size(), 1);
        assertEquals(task1MatrixClocks.get(w4Id), 5);
        IntDoubleVector row1 = (IntDoubleVector) w4ClientForTask0.getRow(0);
        double sum1 = sum(row1.getStorage().getValues());
        assertEquals(sum1, 1000000.0, 0.000001);
        IntDoubleVector row2 = (IntDoubleVector) w4ClientForTask1.getRow(0);
        double sum2 = sum(row2.getStorage().getValues());
        assertEquals(sum2, 1000000.0, 0.000001);
        masterClient.releaseMatrix(w3Meta.getName());
        Thread.sleep(10000);
        matrixw3Proto = matrixMetaManager.getMatrix("w3");
        assertTrue(matrixw3Proto == null);
        MatrixStorageManager matrixStorageManager = LocalClusterContext.get().getPS(psAttempt0Id).getPS().getMatrixStorageManager();
        ServerMatrix sw3 = matrixStorageManager.getMatrix(w3Id);
        assertTrue(sw3 == null);
        w4ClientForTask0.clock().get();
        w4ClientForTask1.clock().get();
        row1 = (IntDoubleVector) w4ClientForTask0.getRow(0);
        sum1 = sum(row1.getStorage().getValues());
        assertEquals(sum1, 1000000.0, 0.000001);
        row2 = (IntDoubleVector) w4ClientForTask1.getRow(0);
        sum2 = sum(row2.getStorage().getValues());
        assertEquals(sum2, 1000000.0, 0.000001);
    } catch (Exception x) {
        LOG.error("run testCreateMatrix failed ", x);
        throw x;
    }
}

Example 7 with AMTaskManager

use of com.tencent.angel.master.task.AMTaskManager in project angel by Tencent.

the class TaskManagerTest method testTaskMatrixClock.

@Test
public void testTaskMatrixClock() throws ServiceException {
    try {
        LOG.info("===========================testTaskMatrixClock===============================");
        AngelApplicationMaster angelAppMaster = LocalClusterContext.get().getMaster().getAppMaster();
        assertTrue(angelAppMaster != null);
        AMTaskManager taskManager = angelAppMaster.getAppContext().getTaskManager();
        Worker worker = LocalClusterContext.get().getWorker(worker0Attempt0Id).getWorker();
        PSAgentMatrixMetaManager matrixMetaManager = worker.getPSAgent().getMatrixMetaManager();
        int w1Id = matrixMetaManager.getMatrixId("w1");
        int w2Id = matrixMetaManager.getMatrixId("w2");
        MasterClient masterClient = worker.getPSAgent().getMasterClient();
        AMTask task0 = taskManager.getTask(task0Id);
        AMTask task1 = taskManager.getTask(task1Id);
        masterClient.updateClock(task0Id.getIndex(), w1Id, 1);
        masterClient.updateClock(task0Id.getIndex(), w2Id, 1);
        Int2IntOpenHashMap matrixClocks = task0.getMatrixClocks();
        assertEquals(matrixClocks.size(), 2);
        assertEquals(matrixClocks.get(w1Id), 1);
        assertEquals(matrixClocks.get(w2Id), 1);
        masterClient.updateClock(task0Id.getIndex(), w1Id, 2);
        assertEquals(task0.getMatrixClock(w1Id), 2);
        assertEquals(task0.getMatrixClock(w2Id), 1);
        masterClient.updateClock(task1Id.getIndex(), w1Id, 1);
        masterClient.updateClock(task1Id.getIndex(), w2Id, 1);
        matrixClocks = task1.getMatrixClocks();
        assertEquals(matrixClocks.size(), 2);
        assertEquals(matrixClocks.get(w1Id), 1);
        assertEquals(matrixClocks.get(w2Id), 1);
        masterClient.updateClock(task1Id.getIndex(), w1Id, 2);
        assertEquals(task1.getMatrixClock(w1Id), 2);
        assertEquals(task1.getMatrixClock(w2Id), 1);
    } catch (Exception x) {
        LOG.error("run testTaskMatrixClock failed ", x);
        throw x;
    }
}

Example 8 with AMTaskManager

use of com.tencent.angel.master.task.AMTaskManager in project angel by Tencent.

the class PSAgentTest method testMasterClient.

@Test
public void testMasterClient() 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();
        PSAgentMatrixMetaManager matrixMetaManager = worker.getPSAgent().getMatrixMetaManager();
        int w1Id = matrixMetaManager.getMatrixId("w1");
        int w2Id = matrixMetaManager.getMatrixId("w2");
        MasterClient masterClient = worker.getPSAgent().getMasterClient();
        assertTrue(masterClient != null);
        Location location = masterClient.getPSLocation(psId);
        String ipRegex = "(2[5][0-5]|2[0-4]\\d|1\\d{2}|\\d{1,2})\\.(25[0-5]|2[0-4]\\d|1\\d{2}|\\d{1,2})\\.(25[0-5]|2[0-4]\\d|1\\d{2}|\\d{1,2})\\.(25[0-5]|2[0-4]\\d|1\\d{2}|\\d{1,2})";
        Pattern pattern = Pattern.compile(ipRegex);
        Matcher matcher = pattern.matcher(location.getIp());
        assertTrue(matcher.matches());
        assertTrue(location.getPort() >= 1 && location.getPort() <= 65535);
        Map<ParameterServerId, Location> psLocations = masterClient.getPSLocations();
        assertEquals(psLocations.size(), 1);
    } catch (Exception x) {
        LOG.error("run testMasterClient failed ", x);
        throw x;
    }
}

Example 9 with AMTaskManager

use of com.tencent.angel.master.task.AMTaskManager 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);
    } catch (Exception x) {
        LOG.error("run testConsistencyController failed ", x);
        throw x;
    }
}

Example 10 with AMTaskManager

use of com.tencent.angel.master.task.AMTaskManager in project angel by Tencent.

the class PSAgentTest method testLocationCache.

@Test
public void testLocationCache() 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();
        PSAgent psAgent = worker.getPSAgent();
        assertTrue(psAgent != null);
        PSAgentLocationManager locationCache = psAgent.getLocationManager();
        assertTrue(locationCache != null);
        // test master location
        Location masterLoc = locationCache.getMasterLocation();
        String ipRegex = "(2[5][0-5]|2[0-4]\\d|1\\d{2}|\\d{1,2})\\.(25[0-5]|2[0-4]\\d|1\\d{2}|\\d{1,2})\\.(25[0-5]|2[0-4]\\d|1\\d{2}|\\d{1,2})\\.(25[0-5]|2[0-4]\\d|1\\d{2}|\\d{1,2})";
        Pattern pattern = Pattern.compile(ipRegex);
        Matcher matcher = pattern.matcher(masterLoc.getIp());
        assertTrue(matcher.matches());
        assertTrue(masterLoc.getPort() >= 1 && masterLoc.getPort() <= 65535);
        // test ps location
        Location psLoc = locationCache.getPsLocation(psId);
        matcher = pattern.matcher(psLoc.getIp());
        assertTrue(matcher.matches());
        assertTrue(psLoc.getPort() >= 1 && psLoc.getPort() <= 65535);
        // assertEquals(psLoc, locationCache.updateAndGetPSLocation(psId));
        // test all ps ids
        ParameterServerId[] allPSIds = locationCache.getPsIds();
        assertEquals(allPSIds.length, 1);
        assertEquals(allPSIds[0], psId);
    } catch (Exception x) {
        LOG.error("run testLocationCache failed ", x);
        throw x;
    }
}