static inline ssize_t health_alarm_log_read(RRDHOST *host, FILE *fp, const char *filename) {
static uint32_t max_unique_id = 0, max_alarm_id = 0;
- ssize_t loaded = -1, updated = -1, errored = -1, duplicate = -1;
errno = 0;
char *s, *buf = mallocz(65536 + 1);
size_t line = 0, len = 0;
- loaded = updated = errored = duplicate = 0;
+ ssize_t loaded = 0, updated = 0, errored = 0, duplicate = 0;
pthread_rwlock_rdlock(&host->health_log.alarm_log_rwlock);
ae->exec_run_timestamp = (uint32_t)strtoul(pointers[11], NULL, 16);
ae->delay_up_to_timestamp = (uint32_t)strtoul(pointers[12], NULL, 16);
- if(unlikely(ae->name)) freez(ae->name);
+ freez(ae->name);
ae->name = strdupz(pointers[13]);
ae->hash_name = simple_hash(ae->name);
- if(unlikely(ae->chart)) freez(ae->chart);
+ freez(ae->chart);
ae->chart = strdupz(pointers[14]);
ae->hash_chart = simple_hash(ae->chart);
- if(unlikely(ae->family)) freez(ae->family);
+ freez(ae->family);
ae->family = strdupz(pointers[15]);
- if(unlikely(ae->exec)) freez(ae->exec);
+ freez(ae->exec);
ae->exec = strdupz(pointers[16]);
if(!*ae->exec) { freez(ae->exec); ae->exec = NULL; }
- if(unlikely(ae->recipient)) freez(ae->recipient);
+ freez(ae->recipient);
ae->recipient = strdupz(pointers[17]);
if(!*ae->recipient) { freez(ae->recipient); ae->recipient = NULL; }
- if(unlikely(ae->source)) freez(ae->source);
+ freez(ae->source);
ae->source = strdupz(pointers[18]);
if(!*ae->source) { freez(ae->source); ae->source = NULL; }
- if(unlikely(ae->units)) freez(ae->units);
+ freez(ae->units);
ae->units = strdupz(pointers[19]);
if(!*ae->units) { freez(ae->units); ae->units = NULL; }
- if(unlikely(ae->info)) freez(ae->info);
+ freez(ae->info);
ae->info = strdupz(pointers[20]);
if(!*ae->info) { freez(ae->info); ae->info = NULL; }
- ae->exec_code = atoi(pointers[21]);
- ae->new_status = atoi(pointers[22]);
- ae->old_status = atoi(pointers[23]);
- ae->delay = atoi(pointers[24]);
+ ae->exec_code = str2i(pointers[21]);
+ ae->new_status = str2i(pointers[22]);
+ ae->old_status = str2i(pointers[23]);
+ ae->delay = str2i(pointers[24]);
- ae->new_value = strtold(pointers[25], NULL);
- ae->old_value = strtold(pointers[26], NULL);
+ ae->new_value = str2l(pointers[25]);
+ ae->old_value = str2l(pointers[26]);
+
+ static char value_string[100 + 1];
+ freez(ae->old_value_string);
+ freez(ae->new_value_string);
+ ae->old_value_string = strdupz(format_value_and_unit(value_string, 100, ae->old_value, ae->units, -1));
+ ae->new_value_string = strdupz(format_value_and_unit(value_string, 100, ae->new_value, ae->units, -1));
// add it to host if not already there
if(unlikely(*pointers[0] == 'A')) {
freez(buf);
- if(!max_unique_id) max_unique_id = (uint32_t)time(NULL);
- if(!max_alarm_id) max_alarm_id = (uint32_t)time(NULL);
+ if(!max_unique_id) max_unique_id = (uint32_t)now_realtime_sec();
+ if(!max_alarm_id) max_alarm_id = (uint32_t)now_realtime_sec();
host->health_log.next_log_id = max_unique_id + 1;
host->health_log.next_alarm_id = max_alarm_id + 1;
// ----------------------------------------------------------------------------
// health alarm log management
-static inline void health_alarm_log(RRDHOST *host,
- uint32_t alarm_id, uint32_t alarm_event_id,
- time_t when,
- const char *name, const char *chart, const char *family,
- const char *exec, const char *recipient, time_t duration,
- calculated_number old_value, calculated_number new_value,
- int old_status, int new_status,
- const char *source,
- const char *units,
- const char *info,
- int delay
+static inline void health_alarm_log(
+ RRDHOST *host,
+ uint32_t alarm_id,
+ uint32_t alarm_event_id,
+ time_t when,
+ const char *name,
+ const char *chart,
+ const char *family,
+ const char *exec,
+ const char *recipient,
+ time_t duration,
+ calculated_number old_value,
+ calculated_number new_value,
+ int old_status,
+ int new_status,
+ const char *source,
+ const char *units,
+ const char *info,
+ int delay,
+ uint32_t flags
) {
debug(D_HEALTH, "Health adding alarm log entry with id: %u", host->health_log.next_log_id);
ae->when = when;
ae->old_value = old_value;
ae->new_value = new_value;
+
+ static char value_string[100 + 1];
+ ae->old_value_string = strdupz(format_value_and_unit(value_string, 100, ae->old_value, ae->units, -1));
+ ae->new_value_string = strdupz(format_value_and_unit(value_string, 100, ae->new_value, ae->units, -1));
+
ae->old_status = old_status;
ae->new_status = new_status;
ae->duration = duration;
ae->delay = delay;
ae->delay_up_to_timestamp = when + delay;
+ ae->flags |= flags;
+
if(ae->old_status == RRDCALC_STATUS_WARNING || ae->old_status == RRDCALC_STATUS_CRITICAL)
ae->non_clear_duration += ae->duration;
if(tree) {
debug(D_VARIABLES, "Deleting variable '%s'", rv->name);
- rrdvar_index_del(tree, rv);
+ if(unlikely(!rrdvar_index_del(tree, rv)))
+ error("Attempted to delete variable '%s' from host '%s', but it is not found.", rv->name, host->hostname);
}
freez(rv->name);
freez(rv);
}
-static inline RRDVAR *rrdvar_create_and_index(const char *scope, avl_tree_lock *tree, const char *name, int type, calculated_number *value) {
+static inline RRDVAR *rrdvar_create_and_index(const char *scope, avl_tree_lock *tree, const char *name, int type, void *value) {
char *variable = strdupz(name);
rrdvar_fix_name(variable);
uint32_t hash = simple_hash(variable);
return rv;
}
+// ----------------------------------------------------------------------------
+// CUSTOM VARIABLES
+
+RRDVAR *rrdvar_custom_host_variable_create(RRDHOST *host, const char *name) {
+ calculated_number *v = callocz(1, sizeof(calculated_number));
+ *v = NAN;
+ RRDVAR *rv = rrdvar_create_and_index("host", &host->variables_root_index, name, RRDVAR_TYPE_CALCULATED_ALLOCATED, v);
+ if(unlikely(!rv)) {
+ free(v);
+ error("Requested variable '%s' already exists - possibly 2 plugins will be updating it at the same time", name);
+
+ char *variable = strdupz(name);
+ rrdvar_fix_name(variable);
+ uint32_t hash = simple_hash(variable);
+
+ rv = rrdvar_index_find(&host->variables_root_index, variable, hash);
+ }
+
+ return rv;
+}
+
+void rrdvar_custom_host_variable_destroy(RRDHOST *host, const char *name) {
+ char *variable = strdupz(name);
+ rrdvar_fix_name(variable);
+ uint32_t hash = simple_hash(variable);
+
+ RRDVAR *rv = rrdvar_index_find(&host->variables_root_index, variable, hash);
+ freez(variable);
+
+ if(!rv) {
+ error("Attempted to remove variable '%s' from host '%s', but it does not exist.", name, host->hostname);
+ return;
+ }
+
+ if(rv->type != RRDVAR_TYPE_CALCULATED_ALLOCATED) {
+ error("Attempted to remove variable '%s' from host '%s', but it does not a custom allocated variable.", name, host->hostname);
+ return;
+ }
+
+ if(!rrdvar_index_del(&host->variables_root_index, rv)) {
+ error("Attempted to remove variable '%s' from host '%s', but it cannot be found.", name, host->hostname);
+ return;
+ }
+
+ freez(rv->name);
+ freez(rv->value);
+ freez(rv);
+}
+
+void rrdvar_custom_host_variable_set(RRDVAR *rv, calculated_number value) {
+ if(rv->type != RRDVAR_TYPE_CALCULATED_ALLOCATED)
+ error("requested to set variable '%s' to value " CALCULATED_NUMBER_FORMAT " but the variable is not a custom one.", rv->name, value);
+ else {
+ calculated_number *v = rv->value;
+ *v = value;
+ }
+}
+
// ----------------------------------------------------------------------------
// RRDVAR lookup
-calculated_number rrdvar2number(RRDVAR *rv) {
+static calculated_number rrdvar2number(RRDVAR *rv) {
switch(rv->type) {
+ case RRDVAR_TYPE_CALCULATED_ALLOCATED:
case RRDVAR_TYPE_CALCULATED: {
calculated_number *n = (calculated_number *)rv->value;
return *n;
}
}
-void dump_variable(void *data) {
- RRDVAR *rv = (RRDVAR *)data;
- debug(D_HEALTH, "%50s : %20.5Lf", rv->name, rrdvar2number(rv));
-}
-
int health_variable_lookup(const char *variable, uint32_t hash, RRDCALC *rc, calculated_number *result) {
RRDSET *st = rc->rrdset;
RRDVAR *rv;
return 1;
}
- debug(D_HEALTH, "Available local chart '%s' variables:", st->id);
- avl_traverse_lock(&st->variables_root_index, dump_variable);
+ return 0;
+}
- debug(D_HEALTH, "Available family '%s' variables:", st->rrdfamily->family);
- avl_traverse_lock(&st->rrdfamily->variables_root_index, dump_variable);
+// ----------------------------------------------------------------------------
+// RRDVAR to JSON
+
+struct variable2json_helper {
+ BUFFER *buf;
+ size_t counter;
+};
+
+static int single_variable2json(void *entry, void *data) {
+ struct variable2json_helper *helper = (struct variable2json_helper *)data;
+ RRDVAR *rv = (RRDVAR *)entry;
+ calculated_number value = rrdvar2number(rv);
+
+ if(unlikely(isnan(value) || isinf(value)))
+ buffer_sprintf(helper->buf, "%s\n\t\t\"%s\": null", helper->counter?",":"", rv->name);
+ else
+ buffer_sprintf(helper->buf, "%s\n\t\t\"%s\": %0.5Lf", helper->counter?",":"", rv->name, (long double)value);
- debug(D_HEALTH, "Available host '%s' variables:", st->rrdhost->hostname);
- avl_traverse_lock(&st->rrdhost->variables_root_index, dump_variable);
+ helper->counter++;
return 0;
}
+void health_api_v1_chart_variables2json(RRDSET *st, BUFFER *buf) {
+ struct variable2json_helper helper = {
+ .buf = buf,
+ .counter = 0
+ };
+
+ buffer_sprintf(buf, "{\n\t\"chart\": \"%s\",\n\t\"chart_name\": \"%s\",\n\t\"chart_context\": \"%s\",\n\t\"chart_variables\": {", st->id, st->name, st->context);
+ avl_traverse_lock(&st->variables_root_index, single_variable2json, (void *)&helper);
+ buffer_sprintf(buf, "\n\t},\n\t\"family\": \"%s\",\n\t\"family_variables\": {", st->family);
+ helper.counter = 0;
+ avl_traverse_lock(&st->rrdfamily->variables_root_index, single_variable2json, (void *)&helper);
+ buffer_sprintf(buf, "\n\t},\n\t\"host\": \"%s\",\n\t\"host_variables\": {", st->rrdhost->hostname);
+ helper.counter = 0;
+ avl_traverse_lock(&st->rrdhost->variables_root_index, single_variable2json, (void *)&helper);
+ buffer_strcat(buf, "\n\t}\n}\n");
+}
+
+
// ----------------------------------------------------------------------------
// RRDDIMVAR management
// DIMENSION VARIABLES
// ----------------------------------------------------------------------------
// RRDCALC management
-static inline const char *rrdcalc_status2string(int status) {
+inline const char *rrdcalc_status2string(int status) {
switch(status) {
case RRDCALC_STATUS_REMOVED:
return "REMOVED";
static void rrdsetcalc_link(RRDSET *st, RRDCALC *rc) {
debug(D_HEALTH, "Health linking alarm '%s.%s' to chart '%s' of host '%s'", rc->chart?rc->chart:"NOCHART", rc->name, st->id, st->rrdhost->hostname);
- rc->last_status_change = time(NULL);
+ rc->last_status_change = now_realtime_sec();
rc->rrdset = st;
rc->rrdset_next = st->alarms;
if(!rc->units) rc->units = strdupz(st->units);
{
- time_t now = time(NULL);
- health_alarm_log(st->rrdhost, rc->id, rc->next_event_id++, now, rc->name, rc->rrdset->id, rc->rrdset->family, rc->exec, rc->recipient, now - rc->last_status_change, rc->old_value, rc->value, rc->status, RRDCALC_STATUS_UNINITIALIZED, rc->source, rc->units, rc->info, 0);
+ time_t now = now_realtime_sec();
+ health_alarm_log(
+ st->rrdhost,
+ rc->id,
+ rc->next_event_id++,
+ now,
+ rc->name,
+ rc->rrdset->id,
+ rc->rrdset->family,
+ rc->exec,
+ rc->recipient,
+ now - rc->last_status_change,
+ rc->old_value,
+ rc->value,
+ rc->status,
+ RRDCALC_STATUS_UNINITIALIZED,
+ rc->source,
+ rc->units,
+ rc->info,
+ 0,
+ 0
+ );
}
}
}
{
- time_t now = time(NULL);
- health_alarm_log(st->rrdhost, rc->id, rc->next_event_id++, now, rc->name, rc->rrdset->id, rc->rrdset->family, rc->exec, rc->recipient, now - rc->last_status_change, rc->old_value, rc->value, rc->status, RRDCALC_STATUS_REMOVED, rc->source, rc->units, rc->info, 0);
+ time_t now = now_realtime_sec();
+ health_alarm_log(
+ st->rrdhost,
+ rc->id,
+ rc->next_event_id++,
+ now,
+ rc->name,
+ rc->rrdset->id,
+ rc->rrdset->family,
+ rc->exec,
+ rc->recipient,
+ now - rc->last_status_change,
+ rc->old_value,
+ rc->value,
+ rc->status,
+ RRDCALC_STATUS_REMOVED,
+ rc->source,
+ rc->units,
+ rc->info,
+ 0,
+ 0
+ );
}
RRDHOST *host = st->rrdhost;
RRDCALCTEMPLATE *rt;
for(rt = st->rrdhost->templates; rt ; rt = rt->next) {
- if(rt->hash_context == st->hash_context && !strcmp(rt->context, st->context)) {
+ if(rt->hash_context == st->hash_context && !strcmp(rt->context, st->context)
+ && (!rt->family_pattern || simple_pattern_matches(rt->family_pattern, st->family))) {
RRDCALC *rc = rrdcalc_create(st->rrdhost, rt, st->id);
if(unlikely(!rc))
error("Health tried to create alarm from template '%s', but it failed", rt->name);
expression_free(rt->warning);
expression_free(rt->critical);
+ freez(rt->family_match);
+ simple_pattern_free(rt->family_pattern);
+
freez(rt->name);
freez(rt->exec);
freez(rt->recipient);
#define HEALTH_ALARM_KEY "alarm"
#define HEALTH_TEMPLATE_KEY "template"
#define HEALTH_ON_KEY "on"
+#define HEALTH_FAMILIES_KEY "families"
#define HEALTH_LOOKUP_KEY "lookup"
#define HEALTH_CALC_KEY "calc"
#define HEALTH_EVERY_KEY "every"
#define HEALTH_UNITS_KEY "units"
#define HEALTH_INFO_KEY "info"
#define HEALTH_DELAY_KEY "delay"
+#define HEALTH_OPTIONS_KEY "options"
static inline int rrdcalc_add_alarm_from_config(RRDHOST *host, RRDCALC *rc) {
if(!rc->chart) {
return 1;
}
+static inline uint32_t health_parse_options(const char *s) {
+ uint32_t options = 0;
+ char buf[100+1] = "";
+
+ while(*s) {
+ buf[0] = '\0';
+
+ // skip spaces
+ while(*s && isspace(*s))
+ s++;
+
+ // find the next space
+ size_t count = 0;
+ while(*s && count < 100 && !isspace(*s))
+ buf[count++] = *s++;
+
+ if(buf[0]) {
+ buf[count] = '\0';
+
+ if(!strcasecmp(buf, "no-clear-notification") || !strcasecmp(buf, "no-clear"))
+ options |= RRDCALC_FLAG_NO_CLEAR_NOTIFICATION;
+ else
+ error("Ignoring unknown alarm option '%s'", buf);
+ }
+ }
+
+ return options;
+}
+
static inline int health_parse_db_lookup(
size_t line, const char *path, const char *file, char *string,
int *group_method, int *after, int *before, int *every,
int health_readfile(const char *path, const char *filename) {
debug(D_HEALTH, "Health configuration reading file '%s/%s'", path, filename);
- static uint32_t hash_alarm = 0, hash_template = 0, hash_on = 0, hash_calc = 0, hash_green = 0, hash_red = 0, hash_warn = 0, hash_crit = 0, hash_exec = 0, hash_every = 0, hash_lookup = 0, hash_units = 0, hash_info = 0, hash_recipient = 0, hash_delay = 0;
+ static uint32_t
+ hash_alarm = 0,
+ hash_template = 0,
+ hash_on = 0,
+ hash_families = 0,
+ hash_calc = 0,
+ hash_green = 0,
+ hash_red = 0,
+ hash_warn = 0,
+ hash_crit = 0,
+ hash_exec = 0,
+ hash_every = 0,
+ hash_lookup = 0,
+ hash_units = 0,
+ hash_info = 0,
+ hash_recipient = 0,
+ hash_delay = 0,
+ hash_options = 0;
+
char buffer[HEALTH_CONF_MAX_LINE + 1];
if(unlikely(!hash_alarm)) {
hash_alarm = simple_uhash(HEALTH_ALARM_KEY);
hash_template = simple_uhash(HEALTH_TEMPLATE_KEY);
hash_on = simple_uhash(HEALTH_ON_KEY);
+ hash_families = simple_uhash(HEALTH_FAMILIES_KEY);
hash_calc = simple_uhash(HEALTH_CALC_KEY);
hash_lookup = simple_uhash(HEALTH_LOOKUP_KEY);
hash_green = simple_uhash(HEALTH_GREEN_KEY);
hash_info = simple_hash(HEALTH_INFO_KEY);
hash_recipient = simple_hash(HEALTH_RECIPIENT_KEY);
hash_delay = simple_uhash(HEALTH_DELAY_KEY);
+ hash_options = simple_uhash(HEALTH_OPTIONS_KEY);
}
snprintfz(buffer, HEALTH_CONF_MAX_LINE, "%s/%s", path, filename);
if(rc->chart) {
if(strcmp(rc->chart, value))
error("Health configuration at line %zu of file '%s/%s' for alarm '%s' has key '%s' twice, once with value '%s' and later with value '%s'. Using ('%s').",
- line, path, filename, rc->name, key, rc->chart, value, value);
+ line, path, filename, rc->name, key, rc->chart, value, value);
freez(rc->chart);
}
else if(hash == hash_delay && !strcasecmp(key, HEALTH_DELAY_KEY)) {
health_parse_delay(line, path, filename, value, &rc->delay_up_duration, &rc->delay_down_duration, &rc->delay_max_duration, &rc->delay_multiplier);
}
+ else if(hash == hash_options && !strcasecmp(key, HEALTH_OPTIONS_KEY)) {
+ rc->options |= health_parse_options(value);
+ }
else {
error("Health configuration at line %zu of file '%s/%s' for alarm '%s' has unknown key '%s'.",
line, path, filename, rc->name, key);
if(rt->context) {
if(strcmp(rt->context, value))
error("Health configuration at line %zu of file '%s/%s' for template '%s' has key '%s' twice, once with value '%s' and later with value '%s'. Using ('%s').",
- line, path, filename, rt->name, key, rt->context, value, value);
+ line, path, filename, rt->name, key, rt->context, value, value);
freez(rt->context);
}
rt->context = tabs2spaces(strdupz(value));
rt->hash_context = simple_hash(rt->context);
}
+ else if(hash == hash_families && !strcasecmp(key, HEALTH_FAMILIES_KEY)) {
+ freez(rt->family_match);
+ simple_pattern_free(rt->family_pattern);
+
+ rt->family_match = tabs2spaces(strdupz(value));
+ rt->family_pattern = simple_pattern_create(rt->family_match, SIMPLE_PATTERN_EXACT);
+ }
else if(hash == hash_lookup && !strcasecmp(key, HEALTH_LOOKUP_KEY)) {
health_parse_db_lookup(line, path, filename, value, &rt->group, &rt->after, &rt->before,
- &rt->update_every,
- &rt->options, &rt->dimensions);
+ &rt->update_every, &rt->options, &rt->dimensions);
}
else if(hash == hash_every && !strcasecmp(key, HEALTH_EVERY_KEY)) {
if(!health_parse_duration(value, &rt->update_every))
else if(hash == hash_delay && !strcasecmp(key, HEALTH_DELAY_KEY)) {
health_parse_delay(line, path, filename, value, &rt->delay_up_duration, &rt->delay_down_duration, &rt->delay_max_duration, &rt->delay_multiplier);
}
+ else if(hash == hash_options && !strcasecmp(key, HEALTH_OPTIONS_KEY)) {
+ rt->options |= health_parse_options(value);
+ }
else {
error("Health configuration at line %zu of file '%s/%s' for template '%s' has unknown key '%s'.",
line, path, filename, rt->name, key);
}
static inline void health_alarm_entry2json_nolock(BUFFER *wb, ALARM_ENTRY *ae, RRDHOST *host) {
- buffer_sprintf(wb, "\n\t{\n"
- "\t\t\"hostname\": \"%s\",\n"
- "\t\t\"unique_id\": %u,\n"
- "\t\t\"alarm_id\": %u,\n"
- "\t\t\"alarm_event_id\": %u,\n"
- "\t\t\"name\": \"%s\",\n"
- "\t\t\"chart\": \"%s\",\n"
- "\t\t\"family\": \"%s\",\n"
- "\t\t\"processed\": %s,\n"
- "\t\t\"updated\": %s,\n"
- "\t\t\"exec_run\": %lu,\n"
- "\t\t\"exec_failed\": %s,\n"
- "\t\t\"exec\": \"%s\",\n"
- "\t\t\"recipient\": \"%s\",\n"
- "\t\t\"exec_code\": %d,\n"
- "\t\t\"source\": \"%s\",\n"
- "\t\t\"units\": \"%s\",\n"
- "\t\t\"info\": \"%s\",\n"
- "\t\t\"when\": %lu,\n"
- "\t\t\"duration\": %lu,\n"
- "\t\t\"non_clear_duration\": %lu,\n"
- "\t\t\"status\": \"%s\",\n"
- "\t\t\"old_status\": \"%s\",\n"
- "\t\t\"delay\": %d,\n"
- "\t\t\"delay_up_to_timestamp\": %lu,\n"
- "\t\t\"updated_by_id\": %u,\n"
- "\t\t\"updates_id\": %u,\n",
- host->hostname,
- ae->unique_id,
- ae->alarm_id,
- ae->alarm_event_id,
- ae->name,
- ae->chart,
- ae->family,
- (ae->flags & HEALTH_ENTRY_FLAG_PROCESSED)?"true":"false",
- (ae->flags & HEALTH_ENTRY_FLAG_UPDATED)?"true":"false",
- (unsigned long)ae->exec_run_timestamp,
- (ae->flags & HEALTH_ENTRY_FLAG_EXEC_FAILED)?"true":"false",
- ae->exec?ae->exec:health.health_default_exec,
- ae->recipient?ae->recipient:health.health_default_recipient,
- ae->exec_code,
- ae->source,
- ae->units?ae->units:"",
- ae->info?ae->info:"",
- (unsigned long)ae->when,
- (unsigned long)ae->duration,
- (unsigned long)ae->non_clear_duration,
- rrdcalc_status2string(ae->new_status),
- rrdcalc_status2string(ae->old_status),
- ae->delay,
- (unsigned long)ae->delay_up_to_timestamp,
- ae->updated_by_id,
- ae->updates_id
+ buffer_sprintf(wb,
+ "\n\t{\n"
+ "\t\t\"hostname\": \"%s\",\n"
+ "\t\t\"unique_id\": %u,\n"
+ "\t\t\"alarm_id\": %u,\n"
+ "\t\t\"alarm_event_id\": %u,\n"
+ "\t\t\"name\": \"%s\",\n"
+ "\t\t\"chart\": \"%s\",\n"
+ "\t\t\"family\": \"%s\",\n"
+ "\t\t\"processed\": %s,\n"
+ "\t\t\"updated\": %s,\n"
+ "\t\t\"exec_run\": %lu,\n"
+ "\t\t\"exec_failed\": %s,\n"
+ "\t\t\"exec\": \"%s\",\n"
+ "\t\t\"recipient\": \"%s\",\n"
+ "\t\t\"exec_code\": %d,\n"
+ "\t\t\"source\": \"%s\",\n"
+ "\t\t\"units\": \"%s\",\n"
+ "\t\t\"info\": \"%s\",\n"
+ "\t\t\"when\": %lu,\n"
+ "\t\t\"duration\": %lu,\n"
+ "\t\t\"non_clear_duration\": %lu,\n"
+ "\t\t\"status\": \"%s\",\n"
+ "\t\t\"old_status\": \"%s\",\n"
+ "\t\t\"delay\": %d,\n"
+ "\t\t\"delay_up_to_timestamp\": %lu,\n"
+ "\t\t\"updated_by_id\": %u,\n"
+ "\t\t\"updates_id\": %u,\n"
+ "\t\t\"value_string\": \"%s\",\n"
+ "\t\t\"old_value_string\": \"%s\",\n"
+ , host->hostname
+ , ae->unique_id
+ , ae->alarm_id
+ , ae->alarm_event_id
+ , ae->name
+ , ae->chart
+ , ae->family
+ , (ae->flags & HEALTH_ENTRY_FLAG_PROCESSED)?"true":"false"
+ , (ae->flags & HEALTH_ENTRY_FLAG_UPDATED)?"true":"false"
+ , (unsigned long)ae->exec_run_timestamp
+ , (ae->flags & HEALTH_ENTRY_FLAG_EXEC_FAILED)?"true":"false"
+ , ae->exec?ae->exec:health.health_default_exec
+ , ae->recipient?ae->recipient:health.health_default_recipient
+ , ae->exec_code
+ , ae->source
+ , ae->units?ae->units:""
+ , ae->info?ae->info:""
+ , (unsigned long)ae->when
+ , (unsigned long)ae->duration
+ , (unsigned long)ae->non_clear_duration
+ , rrdcalc_status2string(ae->new_status)
+ , rrdcalc_status2string(ae->old_status)
+ , ae->delay
+ , (unsigned long)ae->delay_up_to_timestamp
+ , ae->updated_by_id
+ , ae->updates_id
+ , ae->new_value_string
+ , ae->old_value_string
);
+ if(unlikely(ae->flags & HEALTH_ENTRY_FLAG_NO_CLEAR_NOTIFICATION)) {
+ buffer_strcat(wb, "\t\t\"no_clear_notification\": true,\n");
+ }
+
buffer_strcat(wb, "\t\t\"value\":");
buffer_rrd_value(wb, ae->new_value);
buffer_strcat(wb, ",\n");
"\t\t\t\"delay_multiplier\": %f,\n"
"\t\t\t\"delay\": %d,\n"
"\t\t\t\"delay_up_to_timestamp\": %lu,\n"
- , rc->chart, rc->name
- , (unsigned long)rc->id
- , rc->name
- , rc->chart
- , (rc->rrdset && rc->rrdset->family)?rc->rrdset->family:""
- , (rc->rrdset)?"true":"false"
- , rc->exec?rc->exec:health.health_default_exec
- , rc->recipient?rc->recipient:health.health_default_recipient
- , rc->source
- , rc->units?rc->units:""
- , rc->info?rc->info:""
- , rrdcalc_status2string(rc->status)
- , (unsigned long)rc->last_status_change
- , (unsigned long)rc->last_updated
- , (unsigned long)rc->next_update
- , rc->update_every
- , rc->delay_up_duration
- , rc->delay_down_duration
- , rc->delay_max_duration
- , rc->delay_multiplier
- , rc->delay_last
- , (unsigned long)rc->delay_up_to_timestamp
+ , rc->chart, rc->name
+ , (unsigned long)rc->id
+ , rc->name
+ , rc->chart
+ , (rc->rrdset && rc->rrdset->family)?rc->rrdset->family:""
+ , (rc->rrdset)?"true":"false"
+ , rc->exec?rc->exec:health.health_default_exec
+ , rc->recipient?rc->recipient:health.health_default_recipient
+ , rc->source
+ , rc->units?rc->units:""
+ , rc->info?rc->info:""
+ , rrdcalc_status2string(rc->status)
+ , (unsigned long)rc->last_status_change
+ , (unsigned long)rc->last_updated
+ , (unsigned long)rc->next_update
+ , rc->update_every
+ , rc->delay_up_duration
+ , rc->delay_down_duration
+ , rc->delay_max_duration
+ , rc->delay_multiplier
+ , rc->delay_last
+ , (unsigned long)rc->delay_up_to_timestamp
);
+ if(unlikely(rc->options & RRDCALC_FLAG_NO_CLEAR_NOTIFICATION)) {
+ buffer_strcat(wb, "\t\t\t\"no_clear_notification\": true,\n");
+ }
+
if(RRDCALC_HAS_DB_LOOKUP(rc)) {
if(rc->dimensions && *rc->dimensions)
health_string2json(wb, "\t\t\t", "lookup_dimensions", rc->dimensions, ",\n");
host->hostname,
(host->health_log.next_log_id > 0)?(host->health_log.next_log_id - 1):0,
health_enabled?"true":"false",
- (unsigned long)time(NULL));
+ (unsigned long)now_realtime_sec());
RRDCALC *rc;
for(i = 0, rc = host->alarms; rc ; rc = rc->next) {
// health main thread and friends
static inline int rrdcalc_value2status(calculated_number n) {
- if(isnan(n)) return RRDCALC_STATUS_UNDEFINED;
+ if(isnan(n) || isinf(n)) return RRDCALC_STATUS_UNDEFINED;
if(n) return RRDCALC_STATUS_RAISED;
return RRDCALC_STATUS_CLEAR;
}
+#define ALARM_EXEC_COMMAND_LENGTH 8192
+
static inline void health_alarm_execute(RRDHOST *host, ALARM_ENTRY *ae) {
ae->flags |= HEALTH_ENTRY_FLAG_PROCESSED;
if(unlikely(ae->new_status < RRDCALC_STATUS_CLEAR)) {
// do not send notifications for internal statuses
+ debug(D_HEALTH, "Health not sending notification for alarm '%s.%s' status %s (internal statuses)", ae->chart, ae->name, rrdcalc_status2string(ae->new_status));
+ goto done;
+ }
+
+ if(unlikely(ae->new_status <= RRDCALC_STATUS_CLEAR && (ae->flags & HEALTH_ENTRY_FLAG_NO_CLEAR_NOTIFICATION))) {
+ // do not send notifications for disabled statuses
+ debug(D_HEALTH, "Health not sending notification for alarm '%s.%s' status %s (it has no-clear-notification enabled)", ae->chart, ae->name, rrdcalc_status2string(ae->new_status));
+ // mark it as run, so that we will send the same alarm if it happens again
goto done;
}
// find the previous notification for the same alarm
// which we have run the exec script
- ALARM_ENTRY *t;
- for(t = ae->next; t ;t = t->next) {
- if(t->alarm_id == ae->alarm_id && t->flags & HEALTH_ENTRY_FLAG_EXEC_RUN)
- break;
- }
+ // exception: alarms with HEALTH_ENTRY_FLAG_NO_CLEAR_NOTIFICATION set
+ if(likely(!(ae->flags & HEALTH_ENTRY_FLAG_NO_CLEAR_NOTIFICATION))) {
+ uint32_t id = ae->alarm_id;
+ ALARM_ENTRY *t;
+ for(t = ae->next; t ; t = t->next) {
+ if(t->alarm_id == id && t->flags & HEALTH_ENTRY_FLAG_EXEC_RUN)
+ break;
+ }
- if(likely(t)) {
- // we have executed this alarm notification in the past
- if (t && t->new_status == ae->new_status) {
- // don't send the same notification again
- debug(D_HEALTH, "Health not sending again notification for alarm '%s.%s' status %s", ae->chart, ae->name,
- rrdcalc_status2string(ae->new_status));
- goto done;
+ if(likely(t)) {
+ // we have executed this alarm notification in the past
+ if(t && t->new_status == ae->new_status) {
+ // don't send the notification for the same status again
+ debug(D_HEALTH, "Health not sending again notification for alarm '%s.%s' status %s", ae->chart, ae->name
+ , rrdcalc_status2string(ae->new_status));
+ goto done;
+ }
}
- }
- else {
- // we have not executed this alarm notification in the past
- if(unlikely(ae->old_status == RRDCALC_STATUS_UNINITIALIZED && ae->new_status == RRDCALC_STATUS_CLEAR)) {
- debug(D_HEALTH, "Health not sending notification for first initialization of alarm '%s.%s' status %s", ae->chart, ae->name, rrdcalc_status2string(ae->new_status));
- goto done;
+ else {
+ // we have not executed this alarm notification in the past
+ // so, don't send CLEAR notifications
+ if(unlikely(ae->new_status == RRDCALC_STATUS_CLEAR)) {
+ debug(D_HEALTH, "Health not sending notification for first initialization of alarm '%s.%s' status %s"
+ , ae->chart, ae->name, rrdcalc_status2string(ae->new_status));
+ goto done;
+ }
}
}
- char buffer[FILENAME_MAX + 1];
+ static char command_to_run[ALARM_EXEC_COMMAND_LENGTH + 1];
pid_t command_pid;
const char *exec = ae->exec;
const char *recipient = ae->recipient;
if(!recipient) recipient = health.health_default_recipient;
- snprintfz(buffer, FILENAME_MAX, "exec %s '%s' '%s' '%u' '%u' '%u' '%lu' '%s' '%s' '%s' '%s' '%s' '%0.0Lf' '%0.0Lf' '%s' '%u' '%u' '%s' '%s'",
+ snprintfz(command_to_run, ALARM_EXEC_COMMAND_LENGTH, "exec %s '%s' '%s' '%u' '%u' '%u' '%lu' '%s' '%s' '%s' '%s' '%s' '%0.0Lf' '%0.0Lf' '%s' '%u' '%u' '%s' '%s' '%s' '%s'",
exec,
recipient,
host->hostname,
(uint32_t)ae->duration,
(uint32_t)ae->non_clear_duration,
ae->units?ae->units:"",
- ae->info?ae->info:""
+ ae->info?ae->info:"",
+ ae->new_value_string,
+ ae->old_value_string
);
ae->flags |= HEALTH_ENTRY_FLAG_EXEC_RUN;
- ae->exec_run_timestamp = time(NULL);
+ ae->exec_run_timestamp = now_realtime_sec();
- debug(D_HEALTH, "executing command '%s'", buffer);
- FILE *fp = mypopen(buffer, &command_pid);
+ debug(D_HEALTH, "executing command '%s'", command_to_run);
+ FILE *fp = mypopen(command_to_run, &command_pid);
if(!fp) {
- error("HEALTH: Cannot popen(\"%s\", \"r\").", buffer);
+ error("HEALTH: Cannot popen(\"%s\", \"r\").", command_to_run);
goto done;
}
debug(D_HEALTH, "HEALTH reading from command");
- char *s = fgets(buffer, FILENAME_MAX, fp);
+ char *s = fgets(command_to_run, FILENAME_MAX, fp);
(void)s;
ae->exec_code = mypclose(fp, command_pid);
debug(D_HEALTH, "done executing command - returned with code %d", ae->exec_code);
static inline void health_alarm_log_process(RRDHOST *host) {
static uint32_t stop_at_id = 0;
uint32_t first_waiting = (host->health_log.alarms)?host->health_log.alarms->unique_id:0;
- time_t now = time(NULL);
+ time_t now = now_realtime_sec();
pthread_rwlock_rdlock(&host->health_log.alarm_log_rwlock);
freez(ae->source);
freez(ae->units);
freez(ae->info);
+ freez(ae->old_value_string);
+ freez(ae->new_value_string);
freez(ae);
ae = t;
}
void *health_main(void *ptr) {
- (void)ptr;
+ struct netdata_static_thread *static_thread = (struct netdata_static_thread *)ptr;
info("HEALTH thread created with task id %d", gettid());
debug(D_HEALTH, "Health monitoring iteration no %u started", loop);
int oldstate, runnable = 0;
- time_t now = time(NULL);
+ time_t now = now_realtime_sec();
time_t next_run = now + min_run_every;
RRDCALC *rc;
rc->delay_last = delay;
rc->delay_up_to_timestamp = now + delay;
- health_alarm_log(&localhost, rc->id, rc->next_event_id++, now, rc->name, rc->rrdset->id, rc->rrdset->family, rc->exec, rc->recipient, now - rc->last_status_change, rc->old_value, rc->value, rc->status, status, rc->source, rc->units, rc->info, rc->delay_last);
+ health_alarm_log(
+ &localhost,
+ rc->id,
+ rc->next_event_id++,
+ now,
+ rc->name,
+ rc->rrdset->id,
+ rc->rrdset->family,
+ rc->exec,
+ rc->recipient,
+ now - rc->last_status_change,
+ rc->old_value,
+ rc->value,
+ rc->status,
+ status,
+ rc->source,
+ rc->units,
+ rc->info,
+ rc->delay_last,
+ (rc->options & RRDCALC_FLAG_NO_CLEAR_NOTIFICATION)?HEALTH_ENTRY_FLAG_NO_CLEAR_NOTIFICATION:0
+ );
rc->last_status_change = now;
rc->status = status;
}
if(unlikely(netdata_exit))
break;
- now = time(NULL);
+ now = now_realtime_sec();
if(now < next_run) {
debug(D_HEALTH, "Health monitoring iteration no %u done. Next iteration in %d secs",
loop, (int) (next_run - now));
- sleep_usec(1000000 * (unsigned long long) (next_run - now));
+ sleep_usec(USEC_PER_SEC * (usec_t) (next_run - now));
}
else {
debug(D_HEALTH, "Health monitoring iteration no %u done. Next iteration now", loop);
buffer_free(wb);
info("HEALTH thread exiting");
+
+ static_thread->enabled = 0;
pthread_exit(NULL);
return NULL;
}
projects / netdata.git / blobdiff