diff options
author | Costa Tsaousis <costa@netdata.cloud> | 2023-03-02 22:50:48 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-03-02 22:50:48 +0200 |
commit | 021e252fc5d18a7225c0f4c975b3281016861d3c (patch) | |
tree | 63f92adc27419ca9df464635cd85424f52c94179 /health/health.c | |
parent | c4d8d35b9f065f2a847f2780acb4342dabdfd34c (diff) |
/api/v2/contexts (#14592)
* preparation for /api/v2/contexts
* working /api/v2/contexts
* add anomaly rate information in all statistics; when sum-count is requested, return sums and counts instead of averages
* minor fix
* query targegt now accurately counts hosts, contexts, instances, dimensions, metrics
* cleanup /api/v2/contexts
* full text search with /api/v2/contexts
* simple patterns now support the option to search ignoring case
* full text search API with /api/v2/q
* simple pattern execution optimization
* do not show q when not given
* full text search accounting
* separated /api/v2/nodes from /api/v2/contexts
* fix ssv queries for group_by
* count query instances queried and failed per context and host
* split rrdcontext.c to multiple files
* add query totals
* fix anomaly rate calculation; provide "ni" for indexing hosts
* do not generate zero valued members
* faster calculation of anomaly rate; by just summing integers for each db points and doing math once for every generated point
* fix typo when printing dimensions totals
* added option minify to remove spaces and newlines fron JSON output
* send instance ids and names when they differ
* do not add in query target dimensions, instances, contexts and hosts for which there is no retention in the current timeframe
* fix for the previous + renames and code cleanup
* when a dimension is filtered, include in the response all the other dimensions that are selectable
* do not add nodes that do not have retention in the current window
* move selection of dimensions to query_dimension_add(), instead of query_metric_add()
* increase the pre-processing capacity of queries
* generate instance fqdn ids and names only when they are needed
* provide detailed statistics about tiers retention, queries, points, update_every
* late allocation of query dimensions
* cleanup
* more cleanup
* support for annotations per displayed point, RESET and PARTIAL
* new type annotations
* if a chart is not linked to contexts and it is collected, link it when it is collected
* make ML run reentrant
* make ML rrdr query synchronous
* optimize replication memory allocation of replication_sort_entry
* change units to percentage, when requesting a coefficinet of variation, or a percentage query
* initialize replication before starting main threads
* properly decrement no room requests counter
* propagate the non-zero flag to group-by
* the same by avoiding the extra loop
* respect non-zero in all dimension arrays
* remove dictionary garbage collection from dictionary_entries() and dictionary_version()
* be more verbose when jv2 indexing is postponed
* prevent infinite loop
* use hidden dimensions even when dimensions pattern is unset
* traverse hosts using dictionaries
* fix dictionary unittests
Diffstat (limited to 'health/health.c')
-rw-r--r-- | health/health.c | 40 |
1 files changed, 17 insertions, 23 deletions
diff --git a/health/health.c b/health/health.c index 1e20b51b70..4218ede6fb 100644 --- a/health/health.c +++ b/health/health.c @@ -357,13 +357,11 @@ static void health_reload_host(RRDHOST *host) { void health_reload(void) { sql_refresh_hashes(); - rrd_rdlock(); - RRDHOST *host; - rrdhost_foreach_read(host) + dfe_start_reentrant(rrdhost_root_index, host){ health_reload_host(host); - - rrd_unlock(); + } + dfe_done(host); #ifdef ENABLE_ACLK if (netdata_cloud_setting) { @@ -781,7 +779,8 @@ static void initialize_health(RRDHOST *host) else host->health_log.max = (unsigned int)n; - conf_enabled_alarms = simple_pattern_create(config_get(CONFIG_SECTION_HEALTH, "enabled alarms", "*"), NULL, SIMPLE_PATTERN_EXACT); + conf_enabled_alarms = simple_pattern_create(config_get(CONFIG_SECTION_HEALTH, "enabled alarms", "*"), NULL, + SIMPLE_PATTERN_EXACT, true); netdata_rwlock_init(&host->health_log.alarm_log_rwlock); @@ -803,7 +802,7 @@ static void initialize_health(RRDHOST *host) // link the loaded alarms to their charts RRDSET *st; - rrdset_foreach_write(st, host) { + rrdset_foreach_reentrant(st, host) { if (rrdset_flag_check(st, RRDSET_FLAG_ARCHIVED)) continue; @@ -838,11 +837,11 @@ static SILENCE_TYPE check_silenced(RRDCALC *rc, const char *host, SILENCERS *sil for (s = silencers->silencers; s!=NULL; s=s->next){ if ( - (!s->alarms_pattern || (rc->name && s->alarms_pattern && simple_pattern_matches(s->alarms_pattern, rrdcalc_name(rc)))) && - (!s->contexts_pattern || (rc->rrdset && rc->rrdset->context && s->contexts_pattern && simple_pattern_matches(s->contexts_pattern, rrdset_context(rc->rrdset)))) && - (!s->hosts_pattern || (host && s->hosts_pattern && simple_pattern_matches(s->hosts_pattern,host))) && - (!s->charts_pattern || (rc->chart && s->charts_pattern && simple_pattern_matches(s->charts_pattern, rrdcalc_chart_name(rc)))) && - (!s->families_pattern || (rc->rrdset && rc->rrdset->family && s->families_pattern && simple_pattern_matches(s->families_pattern, rrdset_family(rc->rrdset)))) + (!s->alarms_pattern || (rc->name && s->alarms_pattern && simple_pattern_matches_string(s->alarms_pattern, rc->name))) && + (!s->contexts_pattern || (rc->rrdset && rc->rrdset->context && s->contexts_pattern && simple_pattern_matches_string(s->contexts_pattern, rc->rrdset->context))) && + (!s->hosts_pattern || (host && s->hosts_pattern && simple_pattern_matches(s->hosts_pattern, host))) && + (!s->charts_pattern || (rc->chart && s->charts_pattern && simple_pattern_matches_string(s->charts_pattern, rc->chart))) && + (!s->families_pattern || (rc->rrdset && rc->rrdset->family && s->families_pattern && simple_pattern_matches_string(s->families_pattern, rc->rrdset->family))) ) { debug(D_HEALTH, "Alarm matches command API silence entry %s:%s:%s:%s:%s", s->alarms,s->charts, s->contexts, s->hosts, s->families); if (unlikely(silencers->stype == STYPE_NONE)) { @@ -1015,9 +1014,7 @@ void *health_main(void *ptr) { #endif worker_is_busy(WORKER_HEALTH_JOB_RRD_LOCK); - rrd_rdlock(); - - rrdhost_foreach_read(host) { + dfe_start_reentrant(rrdhost_root_index, host) { if(unlikely(!service_running(SERVICE_HEALTH))) break; @@ -1025,11 +1022,8 @@ void *health_main(void *ptr) { if (unlikely(!host->health.health_enabled)) continue; - if (unlikely(!rrdhost_flag_check(host, RRDHOST_FLAG_INITIALIZED_HEALTH))) { - rrd_unlock(); + if (unlikely(!rrdhost_flag_check(host, RRDHOST_FLAG_INITIALIZED_HEALTH))) initialize_health(host); - rrd_rdlock(); - } health_execute_delayed_initializations(host); @@ -1494,9 +1488,8 @@ void *health_main(void *ptr) { } break; } - } //for each host - - rrd_unlock(); + } + dfe_done(host); // wait for all notifications to finish before allowing health to be cleaned up ALARM_ENTRY *ae; @@ -1509,7 +1502,7 @@ void *health_main(void *ptr) { #ifdef ENABLE_ACLK if (netdata_cloud_setting && unlikely(aclk_alert_reloaded) && loop > (marked_aclk_reload_loop + 2)) { - rrdhost_foreach_read(host) { + dfe_start_reentrant(rrdhost_root_index, host) { if(unlikely(!service_running(SERVICE_HEALTH))) break; @@ -1518,6 +1511,7 @@ void *health_main(void *ptr) { sql_queue_removed_alerts_to_aclk(host); } + dfe_done(host); aclk_alert_reloaded = 0; marked_aclk_reload_loop = 0; } |