0
0
Fork 0
mirror of https://github.com/netdata/netdata.git synced 2025-04-25 21:43:55 +00:00
netdata_netdata/ml/Host.h
Costa Tsaousis 5e1b95cf92
Deduplicate all netdata strings ()
* rrdfamily

* rrddim

* rrdset plugin and module names

* rrdset units

* rrdset type

* rrdset family

* rrdset title

* rrdset title more

* rrdset context

* rrdcalctemplate context and removal of context hash from rrdset

* strings statistics

* rrdset name

* rearranged members of rrdset

* eliminate rrdset name hash; rrdcalc chart converted to STRING

* rrdset id, eliminated rrdset hash

* rrdcalc, alarm_entry, alert_config and some of rrdcalctemplate

* rrdcalctemplate

* rrdvar

* eval_variable

* rrddimvar and rrdsetvar

* rrdhost hostname, os and tags

* fix master commits

* added thread cache; implemented string_dup without locks

* faster thread cache

* rrdset and rrddim now use dictionaries for indexing

* rrdhost now uses dictionary

* rrdfamily now uses DICTIONARY

* rrdvar using dictionary instead of AVL

* allocate the right size to rrdvar flag members

* rrdhost remaining char * members to STRING *

* better error handling on indexing

* strings now use a read/write lock to allow parallel searches to the index

* removed AVL support from dictionaries; implemented STRING with native Judy calls

* string releases should be negative

* only 31 bits are allowed for enum flags

* proper locking on strings

* string threading unittest and fixes

* fix lgtm finding

* fixed naming

* stream chart/dimension definitions at the beginning of a streaming session

* thread stack variable is undefined on thread cancel

* rrdcontext garbage collect per host on startup

* worker control in garbage collection

* relaxed deletion of rrdmetrics

* type checking on dictfe

* netdata chart to monitor rrdcontext triggers

* Group chart label updates

* rrdcontext better handling of collected rrdsets

* rrdpush incremental transmition of definitions should use as much buffer as possible

* require 1MB per chart

* empty the sender buffer before enabling metrics streaming

* fill up to 50% of buffer

* reset signaling metrics sending

* use the shared variable for status

* use separate host flag for enabling streaming of metrics

* make sure the flag is clear

* add logging for streaming

* add logging for streaming on buffer overflow

* circular_buffer proper sizing

* removed obsolete logs

* do not execute worker jobs if not necessary

* better messages about compression disabling

* proper use of flags and updating rrdset last access time every time the obsoletion flag is flipped

* monitor stream sender used buffer ratio

* Update exporting unit tests

* no need to compare label value with strcmp

* streaming send workers now monitor bandwidth

* workers now use strings

* streaming receiver monitors incoming bandwidth

* parser shift of worker ids

* minor fixes

* Group chart label updates

* Populate context with dimensions that have data

* Fix chart id

* better shift of parser worker ids

* fix for streaming compression

* properly count received bytes

* ensure LZ4 compression ring buffer does not wrap prematurely

* do not stream empty charts; do not process empty instances in rrdcontext

* need_to_send_chart_definition() does not need an rrdset lock any more

* rrdcontext objects are collected, after data have been written to the db

* better logging of RRDCONTEXT transitions

* always set all variables needed by the worker utilization charts

* implemented double linked list for most objects; eliminated alarm indexes from rrdhost; and many more fixes

* lockless strings design - string_dup() and string_freez() are totally lockless when they dont need to touch Judy - only Judy is protected with a read/write lock

* STRING code re-organization for clarity

* thread_cache improvements; double numbers precision on worker threads

* STRING_ENTRY now shadown STRING, so no duplicate definition is required; string_length() renamed to string_strlen() to follow the paradigm of all other functions, STRING internal statistics are now only compiled with NETDATA_INTERNAL_CHECKS

* rrdhost index by hostname now cleans up; aclk queries of archieved hosts do not index hosts

* Add index to speed up database context searches

* Removed last_updated optimization (was also buggy after latest merge with master)

Co-authored-by: Stelios Fragkakis <52996999+stelfrag@users.noreply.github.com>
Co-authored-by: Vladimir Kobal <vlad@prokk.net>
2022-09-05 19:31:06 +03:00

139 lines
3.2 KiB
C++

// SPDX-License-Identifier: GPL-3.0-or-later
#ifndef ML_HOST_H
#define ML_HOST_H
#include "BitRateWindow.h"
#include "Config.h"
#include "Database.h"
#include "Dimension.h"
#include "ml-private.h"
namespace ml {
class RrdHost {
public:
RrdHost(RRDHOST *RH) : RH(RH) {
AnomalyRateRS = rrdset_create(
RH,
"anomaly_detection",
"anomaly_rates",
NULL, // name
"anomaly_rates",
NULL, // ctx
"Average anomaly rate",
"anomaly rate",
"netdata",
"ml",
39189,
Cfg.DBEngineAnomalyRateEvery,
RRDSET_TYPE_LINE
);
rrdset_flag_set(AnomalyRateRS, RRDSET_FLAG_HIDDEN);
}
RRDHOST *getRH() { return RH; }
unsigned updateEvery() { return RH->rrd_update_every; }
std::string getUUID() {
char S[UUID_STR_LEN];
uuid_unparse_lower(RH->host_uuid, S);
return S;
}
void addDimension(Dimension *D);
void removeDimension(Dimension *D);
void getConfigAsJson(nlohmann::json &Json) const;
virtual ~RrdHost() {};
protected:
RRDHOST *RH;
RRDSET *AnomalyRateRS;
// Protect dimension and lock maps
std::mutex Mutex;
std::unordered_map<RRDDIM *, Dimension *> DimensionsMap;
std::unordered_map<Dimension *, std::mutex> LocksMap;
};
class TrainableHost : public RrdHost {
public:
TrainableHost(RRDHOST *RH) : RrdHost(RH) {}
void train();
void updateResourceUsage() {
std::lock_guard<std::mutex> Lock(ResourceUsageMutex);
getrusage(RUSAGE_THREAD, &ResourceUsage);
}
void getResourceUsage(struct rusage *RU) {
std::lock_guard<std::mutex> Lock(ResourceUsageMutex);
memcpy(RU, &ResourceUsage, sizeof(struct rusage));
}
private:
std::pair<Dimension *, Duration<double>> findDimensionToTrain(const TimePoint &NowTP);
void trainDimension(Dimension *D, const TimePoint &NowTP);
struct rusage ResourceUsage{};
std::mutex ResourceUsageMutex;
};
class DetectableHost : public TrainableHost {
public:
DetectableHost(RRDHOST *RH) : TrainableHost(RH) {}
void startAnomalyDetectionThreads();
void stopAnomalyDetectionThreads();
template<typename ...ArgTypes>
bool getAnomalyInfo(ArgTypes&&... Args) {
return DB.getAnomalyInfo(Args...);
}
template<typename ...ArgTypes>
bool getAnomaliesInRange(ArgTypes&&... Args) {
return DB.getAnomaliesInRange(Args...);
}
void getDetectionInfoAsJson(nlohmann::json &Json) const;
private:
void detect();
void detectOnce();
private:
std::thread TrainingThread;
std::thread DetectionThread;
BitRateWindow BRW{
static_cast<size_t>(Cfg.ADMinWindowSize),
static_cast<size_t>(Cfg.ADMaxWindowSize),
static_cast<size_t>(Cfg.ADIdleWindowSize),
static_cast<size_t>(Cfg.ADMinWindowSize * Cfg.ADWindowRateThreshold)
};
CalculatedNumber WindowAnomalyRate{0.0};
size_t NumAnomalousDimensions{0};
size_t NumNormalDimensions{0};
size_t NumTrainedDimensions{0};
size_t NumActiveDimensions{0};
unsigned AnomalyRateTimer{0};
Database DB{Cfg.AnomalyDBPath};
};
using Host = DetectableHost;
} // namespace ml
#endif /* ML_HOST_H */