test_dist_graph_store.py 10.3 KB
Newer Older
1
2
3
4
5
6
import os
os.environ['OMP_NUM_THREADS'] = '1'
import dgl
import sys
import numpy as np
import time
7
import socket
8
9
10
11
12
13
14
from scipy import sparse as spsp
from numpy.testing import assert_array_equal
from multiprocessing import Process, Manager, Condition, Value
import multiprocessing as mp
from dgl.graph_index import create_graph_index
from dgl.data.utils import load_graphs, save_graphs
from dgl.distributed import DistGraphServer, DistGraph
15
from dgl.distributed import partition_graph, load_partition, load_partition_book, node_split, edge_split
16
17
18
19
import backend as F
import unittest
import pickle

20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
if os.name != 'nt':
    import fcntl
    import struct

def get_local_usable_addr():
    """Get local usable IP and port

    Returns
    -------
    str
        IP address, e.g., '192.168.8.12:50051'
    """
    sock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
    try:
        # doesn't even have to be reachable
        sock.connect(('10.255.255.255', 1))
        ip_addr = sock.getsockname()[0]
    except ValueError:
        ip_addr = '127.0.0.1'
    finally:
        sock.close()
    sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    sock.bind(("", 0))
    sock.listen(1)
    port = sock.getsockname()[1]
    sock.close()

    return ip_addr + ' ' + str(port)

49
50
51
52
53
def create_random_graph(n):
    arr = (spsp.random(n, n, density=0.001, format='coo') != 0).astype(np.int64)
    ig = create_graph_index(arr, readonly=True)
    return dgl.DGLGraph(ig)

54
def run_server(graph_name, server_id, num_clients, shared_mem):
55
    g = DistGraphServer(server_id, "kv_ip_config.txt", num_clients, graph_name,
56
57
                        '/tmp/dist_graph/{}.json'.format(graph_name),
                        disable_shared_mem=not shared_mem)
58
59
60
    print('start server', server_id)
    g.start()

61
62
def run_client(graph_name, part_id, num_nodes, num_edges):
    time.sleep(5)
63
64
65
    gpb = load_partition_book('/tmp/dist_graph/{}.json'.format(graph_name),
                              part_id, None)
    g = DistGraph("kv_ip_config.txt", graph_name, gpb=gpb)
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108

    # Test API
    assert g.number_of_nodes() == num_nodes
    assert g.number_of_edges() == num_edges

    # Test reading node data
    nids = F.arange(0, int(g.number_of_nodes() / 2))
    feats1 = g.ndata['features'][nids]
    feats = F.squeeze(feats1, 1)
    assert np.all(F.asnumpy(feats == nids))

    # Test reading edge data
    eids = F.arange(0, int(g.number_of_edges() / 2))
    feats1 = g.edata['features'][eids]
    feats = F.squeeze(feats1, 1)
    assert np.all(F.asnumpy(feats == eids))

    # Test init node data
    new_shape = (g.number_of_nodes(), 2)
    g.init_ndata('test1', new_shape, F.int32)
    feats = g.ndata['test1'][nids]
    assert np.all(F.asnumpy(feats) == 0)

    # Test init edge data
    new_shape = (g.number_of_edges(), 2)
    g.init_edata('test1', new_shape, F.int32)
    feats = g.edata['test1'][eids]
    assert np.all(F.asnumpy(feats) == 0)

    # Test write data
    new_feats = F.ones((len(nids), 2), F.int32, F.cpu())
    g.ndata['test1'][nids] = new_feats
    feats = g.ndata['test1'][nids]
    assert np.all(F.asnumpy(feats) == 1)

    # Test metadata operations.
    assert len(g.ndata['features']) == g.number_of_nodes()
    assert g.ndata['features'].shape == (g.number_of_nodes(), 1)
    assert g.ndata['features'].dtype == F.int64
    assert g.node_attr_schemes()['features'].dtype == F.int64
    assert g.node_attr_schemes()['test1'].dtype == F.int32
    assert g.node_attr_schemes()['features'].shape == (1,)

109
110
    selected_nodes = np.random.randint(0, 100, size=g.number_of_nodes()) > 30
    # Test node split
111
    nodes = node_split(selected_nodes, g.get_partition_book())
112
113
114
115
116
117
    nodes = F.asnumpy(nodes)
    # We only have one partition, so the local nodes are basically all nodes in the graph.
    local_nids = np.arange(g.number_of_nodes())
    for n in nodes:
        assert n in local_nids

118
119
120
    # clean up
    dgl.distributed.shutdown_servers()
    dgl.distributed.finalize_client()
121
122
    print('end')

123
def check_server_client(shared_mem):
124
    prepare_dist()
125
126
127
128
    g = create_random_graph(10000)

    # Partition the graph
    num_parts = 1
129
    graph_name = 'dist_graph_test_2'
130
131
    g.ndata['features'] = F.unsqueeze(F.arange(0, g.number_of_nodes()), 1)
    g.edata['features'] = F.unsqueeze(F.arange(0, g.number_of_edges()), 1)
132
    partition_graph(g, graph_name, num_parts, '/tmp/dist_graph')
133
134
135
136

    # let's just test on one partition for now.
    # We cannot run multiple servers and clients on the same machine.
    serv_ps = []
137
    ctx = mp.get_context('spawn')
138
    for serv_id in range(1):
139
        p = ctx.Process(target=run_server, args=(graph_name, serv_id, 1, shared_mem))
140
141
142
143
144
145
        serv_ps.append(p)
        p.start()

    cli_ps = []
    for cli_id in range(1):
        print('start client', cli_id)
146
        p = ctx.Process(target=run_client, args=(graph_name, cli_id, g.number_of_nodes(),
147
                                                 g.number_of_edges()))
148
149
150
151
152
        p.start()
        cli_ps.append(p)

    for p in cli_ps:
        p.join()
153
154
155
156

    for p in serv_ps:
        p.join()

157
158
    print('clients have terminated')

159
160
161
162
163
@unittest.skipIf(dgl.backend.backend_name == "tensorflow", reason="TF doesn't support some of operations in DistGraph")
def test_server_client():
    check_server_client(True)
    check_server_client(False)

164
def test_split():
165
    prepare_dist()
166
167
168
    g = create_random_graph(10000)
    num_parts = 4
    num_hops = 2
169
    partition_graph(g, 'dist_graph_test', num_parts, '/tmp/dist_graph', num_hops=num_hops, part_method='metis')
170
171
172
173
174
175

    node_mask = np.random.randint(0, 100, size=g.number_of_nodes()) > 30
    edge_mask = np.random.randint(0, 100, size=g.number_of_edges()) > 30
    selected_nodes = np.nonzero(node_mask)[0]
    selected_edges = np.nonzero(edge_mask)[0]
    for i in range(num_parts):
176
        dgl.distributed.set_num_client(num_parts)
Da Zheng's avatar
Da Zheng committed
177
178
        part_g, node_feats, edge_feats, gpb = load_partition('/tmp/dist_graph/dist_graph_test.json', i)
        local_nids = F.nonzero_1d(part_g.ndata['inner_node'])
179
180
181
182
183
184
185
186
        local_nids = F.gather_row(part_g.ndata[dgl.NID], local_nids)
        nodes1 = np.intersect1d(selected_nodes, F.asnumpy(local_nids))
        nodes2 = node_split(node_mask, gpb, i)
        assert np.all(np.sort(nodes1) == np.sort(F.asnumpy(nodes2)))
        local_nids = F.asnumpy(local_nids)
        for n in nodes1:
            assert n in local_nids

187
188
189
190
191
192
193
        dgl.distributed.set_num_client(num_parts * 2)
        nodes3 = node_split(node_mask, gpb, i * 2)
        nodes4 = node_split(node_mask, gpb, i * 2 + 1)
        nodes5 = F.cat([nodes3, nodes4], 0)
        assert np.all(np.sort(nodes1) == np.sort(F.asnumpy(nodes5)))

        dgl.distributed.set_num_client(num_parts)
Da Zheng's avatar
Da Zheng committed
194
        local_eids = F.nonzero_1d(part_g.edata['inner_edge'])
195
196
197
198
199
200
201
202
        local_eids = F.gather_row(part_g.edata[dgl.EID], local_eids)
        edges1 = np.intersect1d(selected_edges, F.asnumpy(local_eids))
        edges2 = edge_split(edge_mask, gpb, i)
        assert np.all(np.sort(edges1) == np.sort(F.asnumpy(edges2)))
        local_eids = F.asnumpy(local_eids)
        for e in edges1:
            assert e in local_eids

203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
        dgl.distributed.set_num_client(num_parts * 2)
        edges3 = edge_split(edge_mask, gpb, i * 2)
        edges4 = edge_split(edge_mask, gpb, i * 2 + 1)
        edges5 = F.cat([edges3, edges4], 0)
        assert np.all(np.sort(edges1) == np.sort(F.asnumpy(edges5)))

def test_split_even():
    prepare_dist()
    g = create_random_graph(10000)
    num_parts = 4
    num_hops = 2
    partition_graph(g, 'dist_graph_test', num_parts, '/tmp/dist_graph', num_hops=num_hops, part_method='metis')

    node_mask = np.random.randint(0, 100, size=g.number_of_nodes()) > 30
    edge_mask = np.random.randint(0, 100, size=g.number_of_edges()) > 30
    selected_nodes = np.nonzero(node_mask)[0]
    selected_edges = np.nonzero(edge_mask)[0]
    all_nodes1 = []
    all_nodes2 = []
    all_edges1 = []
    all_edges2 = []
    for i in range(num_parts):
        dgl.distributed.set_num_client(num_parts)
        part_g, node_feats, edge_feats, gpb = load_partition('/tmp/dist_graph/dist_graph_test.json', i)
        local_nids = F.nonzero_1d(part_g.ndata['inner_node'])
        local_nids = F.gather_row(part_g.ndata[dgl.NID], local_nids)
        nodes = node_split(node_mask, gpb, i, force_even=True)
        all_nodes1.append(nodes)
        subset = np.intersect1d(F.asnumpy(nodes), F.asnumpy(local_nids))
        print('part {} get {} nodes and {} are in the partition'.format(i, len(nodes), len(subset)))

        dgl.distributed.set_num_client(num_parts * 2)
        nodes1 = node_split(node_mask, gpb, i * 2, force_even=True)
        nodes2 = node_split(node_mask, gpb, i * 2 + 1, force_even=True)
        nodes3 = F.cat([nodes1, nodes2], 0)
        all_nodes2.append(nodes3)
        subset = np.intersect1d(F.asnumpy(nodes), F.asnumpy(nodes3))
        print('intersection has', len(subset))

        dgl.distributed.set_num_client(num_parts)
        local_eids = F.nonzero_1d(part_g.edata['inner_edge'])
        local_eids = F.gather_row(part_g.edata[dgl.EID], local_eids)
        edges = edge_split(edge_mask, gpb, i, force_even=True)
        all_edges1.append(edges)
        subset = np.intersect1d(F.asnumpy(edges), F.asnumpy(local_eids))
        print('part {} get {} edges and {} are in the partition'.format(i, len(edges), len(subset)))

        dgl.distributed.set_num_client(num_parts * 2)
        edges1 = edge_split(edge_mask, gpb, i * 2, force_even=True)
        edges2 = edge_split(edge_mask, gpb, i * 2 + 1, force_even=True)
        edges3 = F.cat([edges1, edges2], 0)
        all_edges2.append(edges3)
        subset = np.intersect1d(F.asnumpy(edges), F.asnumpy(edges3))
        print('intersection has', len(subset))
    all_nodes1 = F.cat(all_nodes1, 0)
    all_edges1 = F.cat(all_edges1, 0)
    all_nodes2 = F.cat(all_nodes2, 0)
    all_edges2 = F.cat(all_edges2, 0)
    all_nodes = np.nonzero(node_mask)[0]
    all_edges = np.nonzero(edge_mask)[0]
    assert np.all(all_nodes == F.asnumpy(all_nodes1))
    assert np.all(all_edges == F.asnumpy(all_edges1))
    assert np.all(all_nodes == F.asnumpy(all_nodes2))
    assert np.all(all_edges == F.asnumpy(all_edges2))

268
269
def prepare_dist():
    ip_config = open("kv_ip_config.txt", "w")
270
271
    ip_addr = get_local_usable_addr()
    ip_config.write('%s 1\n' % ip_addr)
272
273
    ip_config.close()

274
if __name__ == '__main__':
Da Zheng's avatar
Da Zheng committed
275
    os.makedirs('/tmp/dist_graph', exist_ok=True)
276
277
    test_split()
    test_split_even()
Da Zheng's avatar
Da Zheng committed
278
    test_server_client()