diff options
author | Costa Tsaousis <costa@netdata.cloud> | 2022-09-05 19:31:06 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2022-09-05 19:31:06 +0300 |
commit | 5e1b95cf92168c4df74586fb4430dc284806da82 (patch) | |
tree | f42077d8b02eaf316683453a7474bd1f599a833d /ml | |
parent | 544aef1fde6e79ac57d2dea85d3f063076d7f885 (diff) |
Deduplicate all netdata strings (#13570)
* 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>
Diffstat (limited to 'ml')
-rw-r--r-- | ml/Dimension.h | 2 | ||||
-rw-r--r-- | ml/Host.cc | 12 | ||||
-rw-r--r-- | ml/Host.h | 4 | ||||
-rw-r--r-- | ml/ml.cc | 4 |
4 files changed, 10 insertions, 12 deletions
diff --git a/ml/Dimension.h b/ml/Dimension.h index 4fbc09b981..1cc053df3f 100644 --- a/ml/Dimension.h +++ b/ml/Dimension.h @@ -26,7 +26,7 @@ public: RRDSET *RS = RD->rrdset; std::stringstream SS; - SS << RS->context << "|" << RS->id << "|" << RD->name; + SS << rrdset_context(RS) << "|" << rrdset_id(RS) << "|" << rrddim_name(RD); return SS.str(); } diff --git a/ml/Host.cc b/ml/Host.cc index f8cba9d64e..a6f9b330a7 100644 --- a/ml/Host.cc +++ b/ml/Host.cc @@ -23,7 +23,7 @@ static void updateDimensionsChart(RRDHOST *RH, std::stringstream IdSS, NameSS; IdSS << "dimensions_on_" << localhost->machine_guid; - NameSS << "dimensions_on_" << localhost->hostname; + NameSS << "dimensions_on_" << rrdhost_hostname(localhost); RS = rrdset_create( RH, @@ -69,7 +69,7 @@ static void updateRateChart(RRDHOST *RH, collected_number AnomalyRate) { std::stringstream IdSS, NameSS; IdSS << "anomaly_rate_on_" << localhost->machine_guid; - NameSS << "anomaly_rate_on_" << localhost->hostname; + NameSS << "anomaly_rate_on_" << rrdhost_hostname(localhost); RS = rrdset_create( RH, @@ -106,7 +106,7 @@ static void updateWindowLengthChart(RRDHOST *RH, collected_number WindowLength) std::stringstream IdSS, NameSS; IdSS << "detector_window_on_" << localhost->machine_guid; - NameSS << "detector_window_on_" << localhost->hostname; + NameSS << "detector_window_on_" << rrdhost_hostname(localhost); RS = rrdset_create( RH, @@ -147,7 +147,7 @@ static void updateEventsChart(RRDHOST *RH, std::stringstream IdSS, NameSS; IdSS << "detector_events_on_" << localhost->machine_guid; - NameSS << "detector_events_on_" << localhost->hostname; + NameSS << "detector_events_on_" << rrdhost_hostname(localhost); RS = rrdset_create( RH, @@ -193,7 +193,7 @@ static void updateDetectionChart(RRDHOST *RH) { std::stringstream IdSS, NameSS; IdSS << "prediction_stats_" << RH->machine_guid; - NameSS << "prediction_stats_for_" << RH->hostname; + NameSS << "prediction_stats_for_" << rrdhost_hostname(RH); RS = rrdset_create_localhost( "netdata", // type @@ -233,7 +233,7 @@ static void updateTrainingChart(RRDHOST *RH, struct rusage *TRU) std::stringstream IdSS, NameSS; IdSS << "training_stats_" << RH->machine_guid; - NameSS << "training_stats_for_" << RH->hostname; + NameSS << "training_stats_for_" << rrdhost_hostname(RH); RS = rrdset_create_localhost( "netdata", // type @@ -31,9 +31,7 @@ public: RRDSET_TYPE_LINE ); - AnomalyRateRS->flags = static_cast<RRDSET_FLAGS>( - static_cast<int>(AnomalyRateRS->flags) | RRDSET_FLAG_HIDDEN - ); + rrdset_flag_set(AnomalyRateRS, RRDSET_FLAG_HIDDEN); } RRDHOST *getRH() { return RH; } @@ -16,7 +16,7 @@ bool ml_enabled(RRDHOST *RH) { if (!Cfg.EnableAnomalyDetection) return false; - if (simple_pattern_matches(Cfg.SP_HostsToSkip, RH->hostname)) + if (simple_pattern_matches(Cfg.SP_HostsToSkip, rrdhost_hostname(RH))) return false; return true; @@ -76,7 +76,7 @@ void ml_new_dimension(RRDDIM *RD) { if (static_cast<unsigned>(RD->update_every) != H->updateEvery()) return; - if (simple_pattern_matches(Cfg.SP_ChartsToSkip, RS->name)) + if (simple_pattern_matches(Cfg.SP_ChartsToSkip, rrdset_name(RS))) return; Dimension *D = new Dimension(RD); |