File metrics collector end to end test (#832)

examples/v1alpha3/file-metrics-collector/Dockerfile

@@ -0,0 +1,6 @@
+FROM pytorch/pytorch:1.0-cuda10.0-cudnn7-runtime
+
+WORKDIR /var
+ADD mnist.py /var
+
+ENTRYPOINT ["python", "/var/mnist.py"]

examples/v1alpha3/file-metrics-collector/mnist.py

@@ -0,0 +1,148 @@
+from __future__ import print_function
+
+import argparse
+import logging
+import os
+
+from torchvision import datasets, transforms
+import torch
+import torch.distributed as dist
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.optim as optim
+
+WORLD_SIZE = int(os.environ.get('WORLD_SIZE', 1))
+
+logging.basicConfig(filename='/katib/mnist.log', level=logging.DEBUG)
+
+class Net(nn.Module):
+    def __init__(self):
+        super(Net, self).__init__()
+        self.conv1 = nn.Conv2d(1, 20, 5, 1)
+        self.conv2 = nn.Conv2d(20, 50, 5, 1)
+        self.fc1 = nn.Linear(4*4*50, 500)
+        self.fc2 = nn.Linear(500, 10)
+
+    def forward(self, x):
+        x = F.relu(self.conv1(x))
+        x = F.max_pool2d(x, 2, 2)
+        x = F.relu(self.conv2(x))
+        x = F.max_pool2d(x, 2, 2)
+        x = x.view(-1, 4*4*50)
+        x = F.relu(self.fc1(x))
+        x = self.fc2(x)
+        return F.log_softmax(x, dim=1)
+
+def train(args, model, device, train_loader, optimizer, epoch):
+    model.train()
+    for batch_idx, (data, target) in enumerate(train_loader):
+        data, target = data.to(device), target.to(device)
+        optimizer.zero_grad()
+        output = model(data)
+        loss = F.nll_loss(output, target)
+        loss.backward()
+        optimizer.step()
+        if batch_idx % args.log_interval == 0:
+            msg = 'Train Epoch: {} [{}/{} ({:.0f}%)]\tloss={:.4f}'.format(
+                epoch, batch_idx * len(data), len(train_loader.dataset),
+                100. * batch_idx / len(train_loader), loss.item())
+            print(msg)
+            logging.debug(msg)
+            niter = epoch * len(train_loader) + batch_idx
+
+def test(args, model, device, test_loader, epoch):
+    model.eval()
+    test_loss = 0
+    correct = 0
+    with torch.no_grad():
+        for data, target in test_loader:
+            data, target = data.to(device), target.to(device)
+            output = model(data)
+            test_loss += F.nll_loss(output, target, reduction='sum').item() # sum up batch loss
+            pred = output.max(1, keepdim=True)[1] # get the index of the max log-probability
+            correct += pred.eq(target.view_as(pred)).sum().item()
+
+    test_loss /= len(test_loader.dataset)
+    logging.info('\naccuracy={:.4f}\n'.format(float(correct) / len(test_loader.dataset)))
+
+
+def should_distribute():
+    return dist.is_available() and WORLD_SIZE > 1
+
+
+def is_distributed():
+    return dist.is_available() and dist.is_initialized()
+
+
+def main():
+    # Training settings
+    parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
+    parser.add_argument('--batch-size', type=int, default=64, metavar='N',
+                        help='input batch size for training (default: 64)')
+    parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
+                        help='input batch size for testing (default: 1000)')
+    parser.add_argument('--epochs', type=int, default=10, metavar='N',
+                        help='number of epochs to train (default: 10)')
+    parser.add_argument('--lr', type=float, default=0.01, metavar='LR',
+                        help='learning rate (default: 0.01)')
+    parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
+                        help='SGD momentum (default: 0.5)')
+    parser.add_argument('--no-cuda', action='store_true', default=False,
+                        help='disables CUDA training')
+    parser.add_argument('--seed', type=int, default=1, metavar='S',
+                        help='random seed (default: 1)')
+    parser.add_argument('--log-interval', type=int, default=10, metavar='N',
+                        help='how many batches to wait before logging training status')
+    parser.add_argument('--save-model', action='store_true', default=False,
+                        help='For Saving the current Model')
+    if dist.is_available():
+        parser.add_argument('--backend', type=str, help='Distributed backend',
+                            choices=[dist.Backend.GLOO, dist.Backend.NCCL, dist.Backend.MPI],
+                            default=dist.Backend.GLOO)
+    args = parser.parse_args()
+    use_cuda = not args.no_cuda and torch.cuda.is_available()
+    if use_cuda:
+        print('Using CUDA')
+
+    torch.manual_seed(args.seed)
+
+    device = torch.device("cuda" if use_cuda else "cpu")
+
+    if should_distribute():
+        print('Using distributed PyTorch with {} backend'.format(args.backend))
+        dist.init_process_group(backend=args.backend)
+
+    kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
+    train_loader = torch.utils.data.DataLoader(
+        datasets.MNIST('../data', train=True, download=True,
+                       transform=transforms.Compose([
+                           transforms.ToTensor(),
+                           transforms.Normalize((0.1307,), (0.3081,))
+                       ])),
+        batch_size=args.batch_size, shuffle=True, **kwargs)
+    test_loader = torch.utils.data.DataLoader(
+        datasets.MNIST('../data', train=False, transform=transforms.Compose([
+                           transforms.ToTensor(),
+                           transforms.Normalize((0.1307,), (0.3081,))
+                       ])),
+        batch_size=args.test_batch_size, shuffle=False, **kwargs)
+
+    model = Net().to(device)
+
+    if is_distributed():
+        Distributor = nn.parallel.DistributedDataParallel if use_cuda \
+            else nn.parallel.DistributedDataParallelCPU
+        model = Distributor(model)
+
+    optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)
+
+    for epoch in range(1, args.epochs + 1):
+        train(args, model, device, train_loader, optimizer, epoch)
+        test(args, model, device, test_loader, epoch)
+
+    if (args.save_model):
+        torch.save(model.state_dict(),"mnist_cnn.pt")
+
+if __name__ == '__main__':
+    main()
+

examples/v1alpha3/file-metricscollector-example.yaml

@@ -0,0 +1,60 @@
+apiVersion: "kubeflow.org/v1alpha3"
+kind: Experiment
+metadata:
+  namespace: kubeflow
+  labels:
+    controller-tools.k8s.io: "1.0"
+  name: file-metricscollector-example
+spec:
+  objective:
+    type: maximize
+    goal: 0.99
+    objectiveMetricName: accuracy
+  metricsCollectorSpec:
+    source:
+      fileSystemPath:
+        path: "/katib/mnist.log"
+        kind: File
+    collector:
+      kind: File
+  algorithm:
+    algorithmName: random
+  parallelTrialCount: 3
+  maxTrialCount: 12
+  maxFailedTrialCount: 3
+  parameters:
+    - name: --lr
+      parameterType: double
+      feasibleSpace:
+        min: "0.01"
+        max: "0.03"
+    - name: --momentum
+      parameterType: double
+      feasibleSpace:
+        min: "0.3"
+        max: "0.7"
+  trialTemplate:
+    goTemplate:
+        rawTemplate: |-
+          apiVersion: batch/v1
+          kind: Job
+          metadata:
+            name: {{.Trial}}
+            namespace: {{.NameSpace}}
+          spec:
+            template:
+              spec:
+                containers:
+                - name: {{.Trial}}
+                  image: docker.io/liuhougangxa/pytorch-mnist:1.0
+                  imagePullPolicy: Always
+                  command:
+                  - "python"
+                  - "/var/mnist.py"
+                  - "--epochs=1"
+                  {{- with .HyperParameters}}
+                  {{- range .}}
+                  - "{{.Name}}={{.Value}}"
+                  {{- end}}
+                  {{- end}}
+                restartPolicy: Never

test/scripts/v1alpha3/run-file-metricscollector.sh

@@ -0,0 +1,64 @@
+#!/bin/bash
+
+# Copyright 2018 The Kubernetes Authors.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# This shell script is used to build a cluster and create a namespace from our
+# argo workflow
+
+set -o errexit
+set -o nounset
+set -o pipefail
+
+CLUSTER_NAME="${CLUSTER_NAME}"
+ZONE="${GCP_ZONE}"
+PROJECT="${GCP_PROJECT}"
+NAMESPACE="${DEPLOY_NAMESPACE}"
+REGISTRY="${GCP_REGISTRY}"
+GO_DIR=${GOPATH}/src/github.com/${REPO_OWNER}/${REPO_NAME}
+
+echo "Activating service-account"
+gcloud auth activate-service-account --key-file=${GOOGLE_APPLICATION_CREDENTIALS}
+
+echo "Configuring kubectl"
+
+echo "CLUSTER_NAME: ${CLUSTER_NAME}"
+echo "ZONE: ${GCP_ZONE}"
+echo "PROJECT: ${GCP_PROJECT}"
+
+gcloud --project ${PROJECT} container clusters get-credentials ${CLUSTER_NAME} \
+  --zone ${ZONE}
+kubectl config set-context $(kubectl config current-context) --namespace=default
+USER=`gcloud config get-value account`
+
+echo "All Katib components are running."
+kubectl version
+kubectl cluster-info
+echo "Katib deployments"
+kubectl -n kubeflow get deploy
+echo "Katib services"
+kubectl -n kubeflow get svc
+echo "Katib pods"
+kubectl -n kubeflow get pod
+
+cd ${GO_DIR}/test/e2e/v1alpha3
+
+echo "Running e2e file metricscollector experiment"
+export KUBECONFIG=$HOME/.kube/config
+./run-e2e-experiment ../../../examples/v1alpha3/file-metricscollector-example.yaml
+kubectl -n kubeflow describe suggestion
+kubectl delete -f ../../../examples/v1alpha3/file-metricscollector-example.yaml
+kubectl describe pods
+kubectl describe deploy
+exit 0

test/workflows/components/workflows-v1alpha3.libsonnet

@@ -275,6 +275,10 @@
                     name: "run-grid-e2e-tests",
                     template: "run-grid-e2e-tests",
                   },
+                  {
+                    name: "run-file-metricscollector-e2e-tests",
+                    template: "run-file-metricscollector-e2e-tests",
+                  },
                   {
                     name: "run-bayesian-e2e-tests",
                     template: "run-bayesian-e2e-tests",
@@ -355,6 +359,9 @@
             $.parts(namespace, name, overrides).e2e(prow_env, bucket).buildTemplate("run-bayesian-e2e-tests", testWorkerImage, [
               "test/scripts/v1alpha3/run-suggestion-bayesian.sh",
             ]),  // run bayesian algorithm
+            $.parts(namespace, name, overrides).e2e(prow_env, bucket).buildTemplate("run-file-metricscollector-e2e-tests", testWorkerImage, [
+              "test/scripts/v1alpha3/run-file-metricscollector.sh",
+            ]),  // run file metrics collector test
             $.parts(namespace, name, overrides).e2e(prow_env, bucket).buildTemplate("create-pr-symlink", testWorkerImage, [
               "python",
               "-m",