@cryptotaxi247 / netdata-1
Code Commits Issues Pulls Sessions CI/CD
master
master
h 107 lines 3.2 KB
Raw
1 // SPDX-License-Identifier: GPL-3.0-or-later
2
3 #ifndef NETDATA_ML_HOST_H
4 #define NETDATA_ML_HOST_H
5
6 #include "ml_calculated_number.h"
7
8 #include "database/rrd.h"
9
10 #include <atomic>
11 #include <unordered_map>
12
13 struct ml_queue_t;
14
15 typedef struct machine_learning_stats_t {
16 uint32_t num_machine_learning_status_enabled;
17 uint32_t num_machine_learning_status_disabled_sp;
18
19 uint32_t num_metric_type_constant;
20 uint32_t num_metric_type_variable;
21
22 uint32_t num_training_status_untrained;
23 uint32_t num_training_status_pending_without_model;
24 uint32_t num_training_status_trained;
25 uint32_t num_training_status_pending_with_model;
26 uint32_t num_training_status_silenced;
27
28 uint32_t num_anomalous_dimensions;
29 uint32_t num_normal_dimensions;
30 } ml_machine_learning_stats_t;
31
32 typedef struct {
33 RRDDIM *rd;
34 uint32_t normal_dimensions;
35 uint32_t anomalous_dimensions;
36 } ml_context_anomaly_rate_t;
37
38 typedef struct {
39 RRDHOST *rh;
40
41 std::atomic<bool> ml_running;
42
43 // Incremented at the END of every ml_host_stop, after all chart/dim resets
44 // have committed. ml_host_detect_once samples this before and after its
45 // unlocked chart walk; a change means a stop completed during the walk
46 // (so detect raced with stop's chart->mls writes) or a stop+start cycle
47 // happened around the walk. In either case the accumulated snapshot must
48 // be discarded even if ml_running is back to true at the re-check.
49 std::atomic<uint64_t> ml_stop_generation;
50
51 ml_machine_learning_stats_t mls;
52
53 calculated_number_t host_anomaly_rate;
54
55 netdata_mutex_t mutex;
56
57 // Serializes ml_host_start() against ml_host_stop(). Stop holds it across
58 // its full chart/dim reset walk and the final stop-generation bump (it
59 // cannot carry host->mutex into that walk), so a racing start cannot
60 // re-enable ml_running while stop is mid-reset. Without it, a detect walk
61 // could observe ml_running==true with an unchanged stop generation and
62 // publish a snapshot torn by stop's in-flight chart->mls resets.
63 netdata_mutex_t start_stop_mutex;
64
65 ml_queue_t *queue;
66
67 /*
68 * bookkeeping for anomaly detection charts
69 */
70
71 RRDSET *ml_running_rs;
72 RRDDIM *ml_running_rd;
73
74 RRDSET *machine_learning_status_rs;
75 RRDDIM *machine_learning_status_enabled_rd;
76 RRDDIM *machine_learning_status_disabled_sp_rd;
77
78 RRDSET *metric_type_rs;
79 RRDDIM *metric_type_constant_rd;
80 RRDDIM *metric_type_variable_rd;
81
82 RRDSET *training_status_rs;
83 RRDDIM *training_status_untrained_rd;
84 RRDDIM *training_status_pending_without_model_rd;
85 RRDDIM *training_status_trained_rd;
86 RRDDIM *training_status_pending_with_model_rd;
87 RRDDIM *training_status_silenced_rd;
88
89 RRDSET *dimensions_rs;
90 RRDDIM *dimensions_anomalous_rd;
91 RRDDIM *dimensions_normal_rd;
92
93 RRDSET *anomaly_rate_rs;
94 RRDDIM *anomaly_rate_rd;
95
96 RRDSET *detector_events_rs;
97 RRDDIM *detector_events_above_threshold_rd;
98 RRDDIM *detector_events_new_anomaly_event_rd;
99
100 RRDSET *context_anomaly_rate_rs;
101 SPINLOCK context_anomaly_rate_spinlock;
102 std::unordered_map<STRING *, ml_context_anomaly_rate_t> context_anomaly_rate;
103
104 bool reset_pointers;
105 } ml_host_t;
106
107 #endif /* NETDATA_ML_HOST_H */