[fed] Fixes for the encrypted GRPC backend. (#10503)

tests/ci_build/lint_python.py

@@ -34,6 +34,8 @@ class LintersPaths:
         "tests/python/test_with_pandas.py",
         "tests/python-gpu/",
         "tests/python-sycl/",
+        "tests/test_distributed/test_federated/",
+        "tests/test_distributed/test_gpu_federated/",
         "tests/test_distributed/test_with_dask/",
         "tests/test_distributed/test_gpu_with_dask/",
         "tests/test_distributed/test_with_spark/",
@@ -94,6 +96,8 @@ class LintersPaths:
         "tests/python-gpu/load_pickle.py",
         "tests/python-gpu/test_gpu_training_continuation.py",
         "tests/python/test_model_io.py",
+        "tests/test_distributed/test_federated/",
+        "tests/test_distributed/test_gpu_federated/",
         "tests/test_distributed/test_with_spark/test_data.py",
         "tests/test_distributed/test_gpu_with_spark/test_data.py",
         "tests/test_distributed/test_gpu_with_dask/test_gpu_with_dask.py",

tests/ci_build/test_python.sh

@@ -70,6 +70,7 @@ case "$suite" in
     pytest -v -s -rxXs --fulltrace --durations=0 -m "mgpu" ${args} tests/python-gpu
     pytest -v -s -rxXs --fulltrace --durations=0 -m "mgpu" ${args} tests/test_distributed/test_gpu_with_dask
     pytest -v -s -rxXs --fulltrace --durations=0 -m "mgpu" ${args} tests/test_distributed/test_gpu_with_spark
+    pytest -v -s -rxXs --fulltrace --durations=0 -m "mgpu" ${args} tests/test_distributed/test_gpu_federated
     unset_pyspark_envs
     uninstall_xgboost
     set +x
@@ -84,6 +85,7 @@ case "$suite" in
     pytest -v -s -rxXs --fulltrace --durations=0 ${args} tests/python
     pytest -v -s -rxXs --fulltrace --durations=0 ${args} tests/test_distributed/test_with_dask
     pytest -v -s -rxXs --fulltrace --durations=0 ${args} tests/test_distributed/test_with_spark
+    pytest -v -s -rxXs --fulltrace --durations=0 ${args} tests/test_distributed/test_federated
     unset_pyspark_envs
     uninstall_xgboost
     set +x

tests/test_distributed/test_federated/runtests-federated.sh

@@ -1,17 +0,0 @@
-#!/bin/bash
-
-set -e
-
-rm -f ./*.model* ./agaricus* ./*.pem
-
-world_size=$(nvidia-smi -L | wc -l)
-
-# Generate server and client certificates.
-openssl req -x509 -newkey rsa:2048 -days 7 -nodes -keyout server-key.pem -out server-cert.pem -subj "/C=US/CN=localhost"
-openssl req -x509 -newkey rsa:2048 -days 7 -nodes -keyout client-key.pem -out client-cert.pem -subj "/C=US/CN=localhost"
-
-# Split train and test files manually to simulate a federated environment.
-split -n l/"${world_size}" -d ../../../demo/data/agaricus.txt.train agaricus.txt.train-
-split -n l/"${world_size}" -d ../../../demo/data/agaricus.txt.test agaricus.txt.test-
-
-python test_federated.py "${world_size}"

tests/test_distributed/test_federated/test_federated.py

@@ -1,86 +1,8 @@
-#!/usr/bin/python
-import multiprocessing
-import sys
-import time
+import pytest
 
-import xgboost as xgb
-import xgboost.federated
-
-SERVER_KEY = 'server-key.pem'
-SERVER_CERT = 'server-cert.pem'
-CLIENT_KEY = 'client-key.pem'
-CLIENT_CERT = 'client-cert.pem'
+from xgboost.testing.federated import run_federated_learning
 
 
-def run_server(port: int, world_size: int, with_ssl: bool) -> None:
-    if with_ssl:
-        xgboost.federated.run_federated_server(port, world_size, SERVER_KEY, SERVER_CERT,
-                                               CLIENT_CERT)
-    else:
-        xgboost.federated.run_federated_server(port, world_size)
-
-
-def run_worker(port: int, world_size: int, rank: int, with_ssl: bool, with_gpu: bool) -> None:
-    communicator_env = {
-        'xgboost_communicator': 'federated',
-        'federated_server_address': f'localhost:{port}',
-        'federated_world_size': world_size,
-        'federated_rank': rank
-    }
-    if with_ssl:
-        communicator_env['federated_server_cert'] = SERVER_CERT
-        communicator_env['federated_client_key'] = CLIENT_KEY
-        communicator_env['federated_client_cert'] = CLIENT_CERT
-
-    # Always call this before using distributed module
-    with xgb.collective.CommunicatorContext(**communicator_env):
-        # Load file, file will not be sharded in federated mode.
-        dtrain = xgb.DMatrix('agaricus.txt.train-%02d?format=libsvm' % rank)
-        dtest = xgb.DMatrix('agaricus.txt.test-%02d?format=libsvm' % rank)
-
-        # Specify parameters via map, definition are same as c++ version
-        param = {'max_depth': 2, 'eta': 1, 'objective': 'binary:logistic'}
-        if with_gpu:
-            param['tree_method'] = 'hist'
-            param['device'] = f"cuda:{rank}"
-
-        # Specify validations set to watch performance
-        watchlist = [(dtest, 'eval'), (dtrain, 'train')]
-        num_round = 20
-
-        # Run training, all the features in training API is available.
-        bst = xgb.train(param, dtrain, num_round, evals=watchlist,
-                        early_stopping_rounds=2)
-
-        # Save the model, only ask process 0 to save the model.
-        if xgb.collective.get_rank() == 0:
-            bst.save_model("test.model.json")
-            xgb.collective.communicator_print("Finished training\n")
-
-
-def run_federated(with_ssl: bool = True, with_gpu: bool = False) -> None:
-    port = 9091
-    world_size = int(sys.argv[1])
-
-    server = multiprocessing.Process(target=run_server, args=(port, world_size, with_ssl))
-    server.start()
-    time.sleep(1)
-    if not server.is_alive():
-        raise Exception("Error starting Federated Learning server")
-
-    workers = []
-    for rank in range(world_size):
-        worker = multiprocessing.Process(target=run_worker,
-                                         args=(port, world_size, rank, with_ssl, with_gpu))
-        workers.append(worker)
-        worker.start()
-    for worker in workers:
-        worker.join()
-    server.terminate()
-
-
-if __name__ == '__main__':
-    run_federated(with_ssl=True, with_gpu=False)
-    run_federated(with_ssl=False, with_gpu=False)
-    run_federated(with_ssl=True, with_gpu=True)
-    run_federated(with_ssl=False, with_gpu=True)
+@pytest.mark.parametrize("with_ssl", [True, False])
+def test_federated_learning(with_ssl: bool) -> None:
+    run_federated_learning(with_ssl, False, __file__)

tests/test_distributed/test_gpu_federated/test_gpu_federated.py

@@ -0,0 +1,9 @@
+import pytest
+
+from xgboost.testing.federated import run_federated_learning
+
+
+@pytest.mark.parametrize("with_ssl", [True, False])
+@pytest.mark.mgpu
+def test_federated_learning(with_ssl: bool) -> None:
+    run_federated_learning(with_ssl, True, __file__)