summaryrefslogtreecommitdiffstats
path: root/ml/ml.cc
blob: b56401b07ac052303ddafbcf143759a07d8cf2a9 (plain)
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
// SPDX-License-Identifier: GPL-3.0-or-later

#include "Config.h"
#include "Dimension.h"
#include "Host.h"

#include <random>

using namespace ml;

bool ml_capable() {
    return true;
}

bool ml_enabled(RRDHOST *RH) {
    if (!Cfg.EnableAnomalyDetection)
        return false;

    if (simple_pattern_matches(Cfg.SP_HostsToSkip, RH->hostname))
        return false;

    return true;
}

/*
 * Assumptions:
 *  1) hosts outlive their sets, and sets outlive their dimensions,
 *  2) dimensions always have a set that has a host.
 */

void ml_init(void) {
    // Read config values
    Cfg.readMLConfig();

    if (!Cfg.EnableAnomalyDetection)
        return;

    // Generate random numbers to efficiently sample the features we need
    // for KMeans clustering.
    std::random_device RD;
    std::mt19937 Gen(RD());

    Cfg.RandomNums.reserve(Cfg.MaxTrainSamples);
    for (size_t Idx = 0; Idx != Cfg.MaxTrainSamples; Idx++)
        Cfg.RandomNums.push_back(Gen());
}

void ml_new_host(RRDHOST *RH) {
    if (!ml_enabled(RH))
        return;

    Host *H = new Host(RH);
    RH->ml_host = static_cast<ml_host_t>(H);

    H->startAnomalyDetectionThreads();
}

void ml_delete_host(RRDHOST *RH) {
    Host *H = static_cast<Host *>(RH->ml_host);
    if (!H)
        return;

    H->stopAnomalyDetectionThreads();

    delete H;
    RH->ml_host = nullptr;
}

void ml_new_dimension(RRDDIM *RD) {
    RRDSET *RS = RD->rrdset;

    Host *H = static_cast<Host *>(RD->rrdset->rrdhost->ml_host);
    if (!H)
        return;

    if (static_cast<unsigned>(RD->update_every) != H->updateEvery())
        return;

    if (simple_pattern_matches(Cfg.SP_ChartsToSkip, RS->name))
        return;

    Dimension *D = new Dimension(RD);
    RD->state->ml_dimension = static_cast<ml_dimension_t>(D);
    H->addDimension(D);
}

void ml_delete_dimension(RRDDIM *RD) {
    Dimension *D = static_cast<Dimension *>(RD->state->ml_dimension);
    if (!D)
        return;

    Host *H = static_cast<Host *>(RD->rrdset->rrdhost->ml_host);
    if (!H)
        delete D;
    else
        H->removeDimension(D);

    RD->state->ml_dimension = nullptr;
}

char *ml_get_host_info(RRDHOST *RH) {
    nlohmann::json ConfigJson;

    if (RH && RH->ml_host) {
        Host *H = static_cast<Host *>(RH->ml_host);
        H->getConfigAsJson(ConfigJson);
    } else {
        ConfigJson["enabled"] = false;
    }

    return strdup(ConfigJson.dump(2, '\t').c_str());
}

char *ml_get_host_runtime_info(RRDHOST *RH) {
    nlohmann::json ConfigJson;

    if (RH && RH->ml_host) {
        Host *H = static_cast<Host *>(RH->ml_host);
        H->getDetectionInfoAsJson(ConfigJson);
    } else {
        return nullptr;
    }

    return strdup(ConfigJson.dump(1, '\t').c_str());
}

bool ml_is_anomalous(RRDDIM *RD, double Value, bool Exists) {
    Dimension *D = static_cast<Dimension *>(RD->state->ml_dimension);
    if (!D)
        return false;

    D->addValue(Value, Exists);
    bool Result = D->predict().second;
    return Result;
}

char *ml_get_anomaly_events(RRDHOST *RH, const char *AnomalyDetectorName,
                            int AnomalyDetectorVersion, time_t After, time_t Before) {
    if (!RH || !RH->ml_host) {
        error("No host");
        return nullptr;
    }

    Host *H = static_cast<Host *>(RH->ml_host);
    std::vector<std::pair<time_t, time_t>> TimeRanges;

    bool Res = H->getAnomaliesInRange(TimeRanges, AnomalyDetectorName,
                                                  AnomalyDetectorVersion,
                                                  H->getUUID(),
                                                  After, Before);
    if (!Res) {
        error("DB result is empty");
        return nullptr;
    }

    nlohmann::json Json = TimeRanges;
    return strdup(Json.dump(4).c_str());
}

char *ml_get_anomaly_event_info(RRDHOST *RH, const char *AnomalyDetectorName,
                                int AnomalyDetectorVersion, time_t After, time_t Before) {
    if (!RH || !RH->ml_host) {
        error("No host");
        return nullptr;
    }

    Host *H = static_cast<Host *>(RH->ml_host);

    nlohmann::json Json;
    bool Res = H->getAnomalyInfo(Json, AnomalyDetectorName,
                                       AnomalyDetectorVersion,
                                       H->getUUID(),
                                       After, Before);
    if (!Res) {
        error("DB result is empty");
        return nullptr;
    }

    return strdup(Json.dump(4, '\t').c_str());
}

void ml_process_rrdr(RRDR *R, int MaxAnomalyRates) {
    if (R->rows != 1)
        return;

    if (MaxAnomalyRates < 1 || MaxAnomalyRates >= R->d)
        return;

    calculated_number *CNs = R->v;
    RRDR_DIMENSION_FLAGS *DimFlags = R->od;

    std::vector<std::pair<calculated_number, int>> V;

    V.reserve(R->d);
    for (int Idx = 0; Idx != R->d; Idx++)
        V.emplace_back(CNs[Idx], Idx);

    std::sort(V.rbegin(), V.rend());

    for (int Idx = MaxAnomalyRates; Idx != R->d; Idx++) {
        int UnsortedIdx = V[Idx].second;

        int OldFlags = static_cast<int>(DimFlags[UnsortedIdx]);
        int NewFlags = OldFlags | RRDR_DIMENSION_HIDDEN;

        DimFlags[UnsortedIdx] = static_cast<rrdr_dimension_flag>(NewFlags);
    }
}

void ml_dimension_update_name(RRDSET *RS, RRDDIM *RD, const char *Name) {
    (void) RS;

    Dimension *D = static_cast<Dimension *>(RD->state->ml_dimension);
    if (!D)
        return;

    D->setAnomalyRateRDName(Name);
}

bool ml_streaming_enabled() {
    return Cfg.StreamADCharts;
}

#if defined(ENABLE_ML_TESTS)

#include "gtest/gtest.h"

int test_ml(int argc, char *argv[]) {
    (void) argc;
    (void) argv;

    ::testing::InitGoogleTest(&argc, argv);
    return RUN_ALL_TESTS();
}

#endif // ENABLE_ML_TESTS

#include "ml-private.h"