Search in sources :

Example 11 with ServerMatrix

use of com.tencent.angel.ps.storage.matrix.ServerMatrix in project angel by Tencent.

the class PSManagerTest method testPSReport.

@Test
public void testPSReport() throws Exception {
    try {
        ParameterServer ps = LocalClusterContext.get().getPS(psAttempt0Id).getPS();
        Location masterLoc = ps.getMasterLocation();
        TConnection connection = TConnectionManager.getConnection(ps.getConf());
        MasterProtocol master = connection.getMasterService(masterLoc.getIp(), masterLoc.getPort());
        PSReportRequest.Builder builder = PSReportRequest.newBuilder();
        builder.setPsAttemptId(ProtobufUtil.convertToIdProto(psAttempt0Id));
        Pair.Builder pairBuilder = Pair.newBuilder();
        pairBuilder.setKey("ps_key1");
        pairBuilder.setValue("100");
        builder.addMetrics(pairBuilder.build());
        pairBuilder.setKey("ps_key2");
        pairBuilder.setValue("200");
        builder.addMetrics(pairBuilder.build());
        MatrixReportProto.Builder matrixBuilder = MatrixReportProto.newBuilder();
        ConcurrentHashMap<Integer, ServerMatrix> matrixIdMap = ps.getMatrixStorageManager().getMatrices();
        for (Entry<Integer, ServerMatrix> matrixEntry : matrixIdMap.entrySet()) {
            builder.addMatrixReports((matrixBuilder.setMatrixId(matrixEntry.getKey()).setMatrixName(matrixEntry.getValue().getName())));
        }
        PSReportResponse response = master.psReport(null, builder.build());
        assertEquals(response.getPsCommand(), PSCommandProto.PSCOMMAND_OK);
        assertEquals(response.getNeedCreateMatricesCount(), 0);
        assertEquals(response.getNeedReleaseMatrixIdsCount(), 0);
        AngelApplicationMaster angelAppMaster = LocalClusterContext.get().getMaster().getAppMaster();
        ParameterServerManager psManager = angelAppMaster.getAppContext().getParameterServerManager();
        AMParameterServer amPs = psManager.getParameterServer(psId);
        PSAttempt psAttempt = amPs.getPSAttempt(psAttempt0Id);
        Map<String, String> metrices = psAttempt.getMetrices();
        assertTrue(metrices.get("ps_key1").equals("100"));
        assertTrue(metrices.get("ps_key2").equals("200"));
        PSAttemptId psAttempt1Id = new PSAttemptId(psId, 1);
        builder.setPsAttemptId(ProtobufUtil.convertToIdProto(psAttempt1Id));
        response = master.psReport(null, builder.build());
        assertEquals(response.getPsCommand(), PSCommandProto.PSCOMMAND_SHUTDOWN);
    } catch (Exception x) {
        LOG.error("run testPSReport failed ", x);
        throw x;
    }
}
Also used : AMParameterServer(com.tencent.angel.master.ps.ps.AMParameterServer) ServerMatrix(com.tencent.angel.ps.storage.matrix.ServerMatrix) AngelException(com.tencent.angel.exception.AngelException) ParameterServer(com.tencent.angel.ps.ParameterServer) AMParameterServer(com.tencent.angel.master.ps.ps.AMParameterServer) TConnection(com.tencent.angel.ipc.TConnection) PSAttemptId(com.tencent.angel.ps.PSAttemptId) PSAttempt(com.tencent.angel.master.ps.attempt.PSAttempt) ParameterServerManager(com.tencent.angel.master.ps.ParameterServerManager) Location(com.tencent.angel.common.location.Location) Pair(com.tencent.angel.protobuf.generated.MLProtos.Pair) Test(org.junit.Test)

Example 12 with ServerMatrix

use of com.tencent.angel.ps.storage.matrix.ServerMatrix 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;
    }
}
Also used : TaskContext(com.tencent.angel.psagent.task.TaskContext) MasterClient(com.tencent.angel.psagent.client.MasterClient) ServerMatrix(com.tencent.angel.ps.storage.matrix.ServerMatrix) Int2IntOpenHashMap(it.unimi.dsi.fastutil.ints.Int2IntOpenHashMap) AngelException(com.tencent.angel.exception.AngelException) ParameterServer(com.tencent.angel.ps.ParameterServer) IntDoubleVector(com.tencent.angel.ml.math2.vector.IntDoubleVector) PSMatrixMetaManager(com.tencent.angel.ps.meta.PSMatrixMetaManager) IntDoubleDenseVectorStorage(com.tencent.angel.ml.math2.storage.IntDoubleDenseVectorStorage) AMTaskManager(com.tencent.angel.master.task.AMTaskManager) AMMatrixMetaManager(com.tencent.angel.master.matrixmeta.AMMatrixMetaManager) MatrixStorageManager(com.tencent.angel.ps.storage.MatrixStorageManager) Worker(com.tencent.angel.worker.Worker) MatrixClient(com.tencent.angel.psagent.matrix.MatrixClient) AMTask(com.tencent.angel.master.task.AMTask) Test(org.junit.Test)

Example 13 with ServerMatrix

use of com.tencent.angel.ps.storage.matrix.ServerMatrix in project angel by Tencent.

the class GraphMatrixUtils method getPSAnyKeyRow.

public static ServerAnyAnyRow getPSAnyKeyRow(PSContext psContext, PartitionGetParam partParam) {
    ServerMatrix matrix = psContext.getMatrixStorageManager().getMatrix(partParam.getMatrixId());
    ServerPartition part = matrix.getPartition(partParam.getPartKey().getPartitionId());
    return (ServerAnyAnyRow) (((RowBasedPartition) part).getRow(0));
}
Also used : ServerAnyAnyRow(com.tencent.angel.ps.storage.vector.ServerAnyAnyRow) ServerMatrix(com.tencent.angel.ps.storage.matrix.ServerMatrix) RowBasedPartition(com.tencent.angel.ps.storage.partition.RowBasedPartition) ServerPartition(com.tencent.angel.ps.storage.partition.ServerPartition)

Example 14 with ServerMatrix

use of com.tencent.angel.ps.storage.matrix.ServerMatrix in project angel by Tencent.

the class GraphMatrixUtils method getPSLongKeyRow.

public static ServerLongAnyRow getPSLongKeyRow(PSContext psContext, PartitionGetParam partParam) {
    ServerMatrix matrix = psContext.getMatrixStorageManager().getMatrix(partParam.getMatrixId());
    ServerPartition part = matrix.getPartition(partParam.getPartKey().getPartitionId());
    return (ServerLongAnyRow) (((RowBasedPartition) part).getRow(0));
}
Also used : ServerMatrix(com.tencent.angel.ps.storage.matrix.ServerMatrix) RowBasedPartition(com.tencent.angel.ps.storage.partition.RowBasedPartition) ServerLongAnyRow(com.tencent.angel.ps.storage.vector.ServerLongAnyRow) ServerPartition(com.tencent.angel.ps.storage.partition.ServerPartition)

Example 15 with ServerMatrix

use of com.tencent.angel.ps.storage.matrix.ServerMatrix in project angel by Tencent.

the class GraphMatrixUtils method getPSIntKeyRow.

public static ServerIntAnyRow getPSIntKeyRow(PSContext psContext, PartitionUpdateParam partParam) {
    ServerMatrix matrix = psContext.getMatrixStorageManager().getMatrix(partParam.getMatrixId());
    ServerPartition part = matrix.getPartition(partParam.getPartKey().getPartitionId());
    return (ServerIntAnyRow) (((RowBasedPartition) part).getRow(0));
}
Also used : ServerMatrix(com.tencent.angel.ps.storage.matrix.ServerMatrix) RowBasedPartition(com.tencent.angel.ps.storage.partition.RowBasedPartition) ServerIntAnyRow(com.tencent.angel.ps.storage.vector.ServerIntAnyRow) ServerPartition(com.tencent.angel.ps.storage.partition.ServerPartition)

Aggregations

ServerMatrix (com.tencent.angel.ps.storage.matrix.ServerMatrix)39 RowBasedPartition (com.tencent.angel.ps.storage.partition.RowBasedPartition)28 ServerPartition (com.tencent.angel.ps.storage.partition.ServerPartition)22 ServerLongAnyRow (com.tencent.angel.ps.storage.vector.ServerLongAnyRow)15 Long2ObjectMap (it.unimi.dsi.fastutil.longs.Long2ObjectMap)5 Random (java.util.Random)5 ServerIntAnyRow (com.tencent.angel.ps.storage.vector.ServerIntAnyRow)4 CSRPartition (com.tencent.angel.ps.storage.partition.CSRPartition)3 IntCSRStorage (com.tencent.angel.ps.storage.partition.storage.IntCSRStorage)3 ServerLongIntRow (com.tencent.angel.ps.storage.vector.ServerLongIntRow)3 AngelException (com.tencent.angel.exception.AngelException)2 MatrixFormat (com.tencent.angel.model.output.format.MatrixFormat)2 Pair (com.tencent.angel.protobuf.generated.MLProtos.Pair)2 ParameterServer (com.tencent.angel.ps.ParameterServer)2 ObjectNotFoundException (com.tencent.angel.ps.server.data.exception.ObjectNotFoundException)2 MatrixStorageManager (com.tencent.angel.ps.storage.MatrixStorageManager)2 ServerAnyAnyRow (com.tencent.angel.ps.storage.vector.ServerAnyAnyRow)2 ServerLongLongRow (com.tencent.angel.ps.storage.vector.ServerLongLongRow)2 ServerRow (com.tencent.angel.ps.storage.vector.ServerRow)2 LongArrayElement (com.tencent.angel.ps.storage.vector.element.LongArrayElement)2