aboutsummaryrefslogtreecommitdiffstats
path: root/swarm/network/stream/snapshot_retrieval_test.go
blob: 6498f599dcc8f385e8b5c5ca461d8e487a0b9128 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
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
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
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
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
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
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
// Copyright 2018 The go-ethereum Authors
// This file is part of the go-ethereum library.
//
// The go-ethereum library is free software: you can redistribute it and/or modify
// it under the terms of the GNU Lesser General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// The go-ethereum library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Lesser General Public License for more details.
//
// You should have received a copy of the GNU Lesser General Public License
// along with the go-ethereum library. If not, see <http://www.gnu.org/licenses/>.
package stream

import (
    "context"
    "fmt"
    "os"
    "sync"
    "testing"
    "time"

    "github.com/ethereum/go-ethereum/node"
    "github.com/ethereum/go-ethereum/p2p/enode"
    "github.com/ethereum/go-ethereum/p2p/simulations/adapters"
    "github.com/ethereum/go-ethereum/swarm/log"
    "github.com/ethereum/go-ethereum/swarm/network"
    "github.com/ethereum/go-ethereum/swarm/network/simulation"
    "github.com/ethereum/go-ethereum/swarm/state"
    "github.com/ethereum/go-ethereum/swarm/storage"
)

//constants for random file generation
const (
    minFileSize = 2
    maxFileSize = 40
)

//This test is a retrieval test for nodes.
//A configurable number of nodes can be
//provided to the test.
//Files are uploaded to nodes, other nodes try to retrieve the file
//Number of nodes can be provided via commandline too.
func TestFileRetrieval(t *testing.T) {
    if *nodes != 0 {
        err := runFileRetrievalTest(*nodes)
        if err != nil {
            t.Fatal(err)
        }
    } else {
        nodeCnt := []int{16}
        //if the `longrunning` flag has been provided
        //run more test combinations
        if *longrunning {
            nodeCnt = append(nodeCnt, 32, 64, 128)
        }
        for _, n := range nodeCnt {
            err := runFileRetrievalTest(n)
            if err != nil {
                t.Fatal(err)
            }
        }
    }
}

//This test is a retrieval test for nodes.
//One node is randomly selected to be the pivot node.
//A configurable number of chunks and nodes can be
//provided to the test, the number of chunks is uploaded
//to the pivot node and other nodes try to retrieve the chunk(s).
//Number of chunks and nodes can be provided via commandline too.
func TestRetrieval(t *testing.T) {
    //if nodes/chunks have been provided via commandline,
    //run the tests with these values
    if *nodes != 0 && *chunks != 0 {
        err := runRetrievalTest(*chunks, *nodes)
        if err != nil {
            t.Fatal(err)
        }
    } else {
        var nodeCnt []int
        var chnkCnt []int
        //if the `longrunning` flag has been provided
        //run more test combinations
        if *longrunning {
            nodeCnt = []int{16, 32, 128}
            chnkCnt = []int{4, 32, 256}
        } else {
            //default test
            nodeCnt = []int{16}
            chnkCnt = []int{32}
        }
        for _, n := range nodeCnt {
            for _, c := range chnkCnt {
                err := runRetrievalTest(c, n)
                if err != nil {
                    t.Fatal(err)
                }
            }
        }
    }
}

/*

The test loads a snapshot file to construct the swarm network,
assuming that the snapshot file identifies a healthy
kademlia network. Nevertheless a health check runs in the
simulation's `action` function.

The snapshot should have 'streamer' in its service list.
*/
func runFileRetrievalTest(nodeCount int) error {
    sim := simulation.New(map[string]simulation.ServiceFunc{
        "streamer": func(ctx *adapters.ServiceContext, bucket *sync.Map) (s node.Service, cleanup func(), err error) {
            node := ctx.Config.Node()
            addr := network.NewAddr(node)
            store, datadir, err := createTestLocalStorageForID(node.ID(), addr)
            if err != nil {
                return nil, nil, err
            }
            bucket.Store(bucketKeyStore, store)

            localStore := store.(*storage.LocalStore)
            netStore, err := storage.NewNetStore(localStore, nil)
            if err != nil {
                return nil, nil, err
            }
            kad := network.NewKademlia(addr.Over(), network.NewKadParams())
            delivery := NewDelivery(kad, netStore)
            netStore.NewNetFetcherFunc = network.NewFetcherFactory(delivery.RequestFromPeers, true).New

            r := NewRegistry(addr.ID(), delivery, netStore, state.NewInmemoryStore(), &RegistryOptions{
                DoSync:          true,
                SyncUpdateDelay: 3 * time.Second,
            })

            fileStore := storage.NewFileStore(netStore, storage.NewFileStoreParams())
            bucket.Store(bucketKeyFileStore, fileStore)

            cleanup = func() {
                os.RemoveAll(datadir)
                netStore.Close()
                r.Close()
            }

            return r, cleanup, nil

        },
    })
    defer sim.Close()

    log.Info("Initializing test config")

    conf := &synctestConfig{}
    //map of discover ID to indexes of chunks expected at that ID
    conf.idToChunksMap = make(map[enode.ID][]int)
    //map of overlay address to discover ID
    conf.addrToIDMap = make(map[string]enode.ID)
    //array where the generated chunk hashes will be stored
    conf.hashes = make([]storage.Address, 0)

    err := sim.UploadSnapshot(fmt.Sprintf("testing/snapshot_%d.json", nodeCount))
    if err != nil {
        return err
    }

    ctx, cancelSimRun := context.WithTimeout(context.Background(), 1*time.Minute)
    defer cancelSimRun()

    result := sim.Run(ctx, func(ctx context.Context, sim *simulation.Simulation) error {
        nodeIDs := sim.UpNodeIDs()
        for _, n := range nodeIDs {
            //get the kademlia overlay address from this ID
            a := n.Bytes()
            //append it to the array of all overlay addresses
            conf.addrs = append(conf.addrs, a)
            //the proximity calculation is on overlay addr,
            //the p2p/simulations check func triggers on enode.ID,
            //so we need to know which overlay addr maps to which nodeID
            conf.addrToIDMap[string(a)] = n
        }

        //an array for the random files
        var randomFiles []string
        //channel to signal when the upload has finished
        //uploadFinished := make(chan struct{})
        //channel to trigger new node checks

        conf.hashes, randomFiles, err = uploadFilesToNodes(sim)
        if err != nil {
            return err
        }
        if _, err := sim.WaitTillHealthy(ctx, 2); err != nil {
            return err
        }

        // File retrieval check is repeated until all uploaded files are retrieved from all nodes
        // or until the timeout is reached.
        allSuccess := false
        for !allSuccess {
            for _, id := range nodeIDs {
                //for each expected chunk, check if it is in the local store
                localChunks := conf.idToChunksMap[id]
                localSuccess := true
                for _, ch := range localChunks {
                    //get the real chunk by the index in the index array
                    chunk := conf.hashes[ch]
                    log.Trace(fmt.Sprintf("node has chunk: %s:", chunk))
                    //check if the expected chunk is indeed in the localstore
                    var err error
                    //check on the node's FileStore (netstore)
                    item, ok := sim.NodeItem(id, bucketKeyFileStore)
                    if !ok {
                        return fmt.Errorf("No registry")
                    }
                    fileStore := item.(*storage.FileStore)
                    //check all chunks
                    for i, hash := range conf.hashes {
                        reader, _ := fileStore.Retrieve(context.TODO(), hash)
                        //check that we can read the file size and that it corresponds to the generated file size
                        if s, err := reader.Size(ctx, nil); err != nil || s != int64(len(randomFiles[i])) {
                            allSuccess = false
                            log.Warn("Retrieve error", "err", err, "hash", hash, "nodeId", id)
                        } else {
                            log.Debug(fmt.Sprintf("File with root hash %x successfully retrieved", hash))
                        }
                    }
                    if err != nil {
                        log.Warn(fmt.Sprintf("Chunk %s NOT found for id %s", chunk, id))
                        localSuccess = false
                    } else {
                        log.Debug(fmt.Sprintf("Chunk %s IS FOUND for id %s", chunk, id))
                    }
                }
                allSuccess = localSuccess
            }
        }
        if !allSuccess {
            return fmt.Errorf("Not all chunks succeeded!")
        }
        return nil
    })

    if result.Error != nil {
        return result.Error
    }

    return nil
}

/*
The test generates the given number of chunks.

The test loads a snapshot file to construct the swarm network,
assuming that the snapshot file identifies a healthy
kademlia network. Nevertheless a health check runs in the
simulation's `action` function.

The snapshot should have 'streamer' in its service list.
*/
func runRetrievalTest(chunkCount int, nodeCount int) error {
    sim := simulation.New(map[string]simulation.ServiceFunc{
        "streamer": func(ctx *adapters.ServiceContext, bucket *sync.Map) (s node.Service, cleanup func(), err error) {
            node := ctx.Config.Node()
            addr := network.NewAddr(node)
            store, datadir, err := createTestLocalStorageForID(node.ID(), addr)
            if err != nil {
                return nil, nil, err
            }
            bucket.Store(bucketKeyStore, store)

            localStore := store.(*storage.LocalStore)
            netStore, err := storage.NewNetStore(localStore, nil)
            if err != nil {
                return nil, nil, err
            }
            kad := network.NewKademlia(addr.Over(), network.NewKadParams())
            delivery := NewDelivery(kad, netStore)
            netStore.NewNetFetcherFunc = network.NewFetcherFactory(delivery.RequestFromPeers, true).New

            r := NewRegistry(addr.ID(), delivery, netStore, state.NewInmemoryStore(), &RegistryOptions{
                DoSync:          true,
                SyncUpdateDelay: 0,
            })

            fileStore := storage.NewFileStore(netStore, storage.NewFileStoreParams())
            bucketKeyFileStore = simulation.BucketKey("filestore")
            bucket.Store(bucketKeyFileStore, fileStore)

            cleanup = func() {
                os.RemoveAll(datadir)
                netStore.Close()
                r.Close()
            }

            return r, cleanup, nil

        },
    })
    defer sim.Close()

    conf := &synctestConfig{}
    //map of discover ID to indexes of chunks expected at that ID
    conf.idToChunksMap = make(map[enode.ID][]int)
    //map of overlay address to discover ID
    conf.addrToIDMap = make(map[string]enode.ID)
    //array where the generated chunk hashes will be stored
    conf.hashes = make([]storage.Address, 0)

    err := sim.UploadSnapshot(fmt.Sprintf("testing/snapshot_%d.json", nodeCount))
    if err != nil {
        return err
    }

    ctx := context.Background()
    result := sim.Run(ctx, func(ctx context.Context, sim *simulation.Simulation) error {
        nodeIDs := sim.UpNodeIDs()
        for _, n := range nodeIDs {
            //get the kademlia overlay address from this ID
            a := n.Bytes()
            //append it to the array of all overlay addresses
            conf.addrs = append(conf.addrs, a)
            //the proximity calculation is on overlay addr,
            //the p2p/simulations check func triggers on enode.ID,
            //so we need to know which overlay addr maps to which nodeID
            conf.addrToIDMap[string(a)] = n
        }

        //an array for the random files
        var randomFiles []string
        //this is the node selected for upload
        node := sim.RandomUpNode()
        item, ok := sim.NodeItem(node.ID, bucketKeyStore)
        if !ok {
            return fmt.Errorf("No localstore")
        }
        lstore := item.(*storage.LocalStore)
        conf.hashes, err = uploadFileToSingleNodeStore(node.ID, chunkCount, lstore)
        if err != nil {
            return err
        }
        if _, err := sim.WaitTillHealthy(ctx, 2); err != nil {
            return err
        }

        // File retrieval check is repeated until all uploaded files are retrieved from all nodes
        // or until the timeout is reached.
        allSuccess := false
        for !allSuccess {
            for _, id := range nodeIDs {
                //for each expected chunk, check if it is in the local store
                localChunks := conf.idToChunksMap[id]
                localSuccess := true
                for _, ch := range localChunks {
                    //get the real chunk by the index in the index array
                    chunk := conf.hashes[ch]
                    log.Trace(fmt.Sprintf("node has chunk: %s:", chunk))
                    //check if the expected chunk is indeed in the localstore
                    var err error
                    //check on the node's FileStore (netstore)
                    item, ok := sim.NodeItem(id, bucketKeyFileStore)
                    if !ok {
                        return fmt.Errorf("No registry")
                    }
                    fileStore := item.(*storage.FileStore)
                    //check all chunks
                    for i, hash := range conf.hashes {
                        reader, _ := fileStore.Retrieve(context.TODO(), hash)
                        //check that we can read the file size and that it corresponds to the generated file size
                        if s, err := reader.Size(ctx, nil); err != nil || s != int64(len(randomFiles[i])) {
                            allSuccess = false
                            log.Warn("Retrieve error", "err", err, "hash", hash, "nodeId", id)
                        } else {
                            log.Debug(fmt.Sprintf("File with root hash %x successfully retrieved", hash))
                        }
                    }
                    if err != nil {
                        log.Warn(fmt.Sprintf("Chunk %s NOT found for id %s", chunk, id))
                        localSuccess = false
                    } else {
                        log.Debug(fmt.Sprintf("Chunk %s IS FOUND for id %s", chunk, id))
                    }
                }
                allSuccess = localSuccess
            }
        }
        if !allSuccess {
            return fmt.Errorf("Not all chunks succeeded!")
        }
        return nil
    })

    if result.Error != nil {
        return result.Error
    }

    return nil
}