@cryptotaxi247 / netdata-1 / commits / ba47e1970

New alarms (exporting and Backend) (#9075)

New alarms for exporting and backend.

thiagoftsm committed May 26, 2020 at 11:57 UTC ba47e197056601c7db3ce8db0db277d155e8118a
4 files changed +51 -5
exporting/send_internal_metrics.c
+5 -5
@@ -15,7 +15,7 @@ void create_main_rusage_chart(RRDSET **st_rusage, RRDDIM **rd_user, RRDDIM **rd_
15 return;
16
17 *st_rusage = rrdset_create_localhost(
18 - "netdata", "exporting_main_thread_cpu", NULL, "exporting", NULL, "Netdata Main Exporting Thread CPU Usage",
18 + "netdata", "exporting_main_thread_cpu", NULL, "exporting", "exporting_cpu_usage", "Netdata Main Exporting Thread CPU Usage",
19 "milliseconds/s", "exporting", NULL, 130600, localhost->rrd_update_every, RRDSET_TYPE_STACKED);
20
21 *rd_user = rrddim_add(*st_rusage, "user", NULL, 1, 1000, RRD_ALGORITHM_INCREMENTAL);
@@ -67,7 +67,7 @@ void send_internal_metrics(struct instance *instance)
67 netdata_fix_chart_id(id);
68
69 stats->st_metrics = rrdset_create_localhost(
70 - "netdata", id, NULL, buffer_tostring(family), NULL, "Netdata Buffered Metrics", "metrics", "exporting", NULL,
70 + "netdata", id, NULL, buffer_tostring(family), "exporting_buffer", "Netdata Buffered Metrics", "metrics", "exporting", NULL,
71 130610, instance->config.update_every, RRDSET_TYPE_LINE);
72
73 stats->rd_buffered_metrics = rrddim_add(stats->st_metrics, "buffered", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE);
@@ -80,7 +80,7 @@ void send_internal_metrics(struct instance *instance)
80 netdata_fix_chart_id(id);
81
82 stats->st_bytes = rrdset_create_localhost(
83 - "netdata", id, NULL, buffer_tostring(family), NULL, "Netdata Exporting Data Size", "KiB", "exporting", NULL,
83 + "netdata", id, NULL, buffer_tostring(family), "exporting_data_size", "Netdata Exporting Data Size", "KiB", "exporting", NULL,
84 130620, instance->config.update_every, RRDSET_TYPE_AREA);
85
86 stats->rd_buffered_bytes = rrddim_add(stats->st_bytes, "buffered", NULL, 1, 1024, RRD_ALGORITHM_ABSOLUTE);
@@ -94,7 +94,7 @@ void send_internal_metrics(struct instance *instance)
94 netdata_fix_chart_id(id);
95
96 stats->st_ops = rrdset_create_localhost(
97 - "netdata", id, NULL, buffer_tostring(family), NULL, "Netdata Exporting Operations", "operations", "exporting",
97 + "netdata", id, NULL, buffer_tostring(family), "exporting_operations", "Netdata Exporting Operations", "operations", "exporting",
98 NULL, 130630, instance->config.update_every, RRDSET_TYPE_LINE);
99
100 stats->rd_transmission_successes = rrddim_add(stats->st_ops, "write", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE);
@@ -109,7 +109,7 @@ void send_internal_metrics(struct instance *instance)
109 netdata_fix_chart_id(id);
110
111 stats->st_rusage = rrdset_create_localhost(
112 - "netdata", id, NULL, buffer_tostring(family), NULL, "Netdata Exporting Instance Thread CPU Usage",
112 + "netdata", id, NULL, buffer_tostring(family), "exporting_instance", "Netdata Exporting Instance Thread CPU Usage",
113 "milliseconds/s", "exporting", NULL, 130640, instance->config.update_every, RRDSET_TYPE_STACKED);
114
115 stats->rd_user = rrddim_add(stats->st_rusage, "user", NULL, 1, 1000, RRD_ALGORITHM_INCREMENTAL);
health/Makefile.am
+1
@@ -45,6 +45,7 @@ dist_healthconfig_DATA = \
45 health.d/dockerd.conf \
46 health.d/elasticsearch.conf \
47 health.d/entropy.conf \
48 + health.d/exporting.conf \
49 health.d/fping.conf \
50 health.d/ioping.conf \
51 health.d/fronius.conf \
health/health.d/backend.conf
+11
@@ -1,3 +1,13 @@
1 +# Alert that backends subsystem will be disabled soon
2 + alarm: backend_metrics_eol
3 + on: netdata.backend_metrics
4 + units: boolean
5 + calc: $now - $last_collected_t
6 + every: 1m
7 + warn: $this > 0
8 + delay: down 5m multiplier 1.5 max 1h
9 + info: The backends subsystem is deprecated and will be removed soon. Migrate your configuration to exporting.conf.
10 + to: sysadmin
11
12 # make sure we are sending data to backend
13
@@ -32,6 +42,7 @@
42 info: number of metrics lost due to repeating failures to contact the backend server
43 to: dba
44
45 +
46 # this chart has been removed from netdata
47 # alarm: backend_slow
48 # on: netdata.backend_latency
health/health.d/exporting.conf new
+34
@@ -0,0 +1,34 @@
1 +
2 +template: exporting_last_buffering
3 +families: *
4 + on: exporting_data_size
5 + calc: $now - $last_collected_t
6 + units: seconds ago
7 + every: 10s
8 + warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
9 + crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
10 + delay: down 5m multiplier 1.5 max 1h
11 + info: number of seconds since the last successful buffering of exporting data
12 + to: dba
13 +
14 +template: exporting_metrics_sent
15 +families: *
16 + on: exporting_data_size
17 + units: %
18 + calc: abs($sent) * 100 / abs($buffered)
19 + every: 10s
20 + warn: $this != 100
21 + delay: down 5m multiplier 1.5 max 1h
22 + info: percentage of metrics sent to the external database server
23 + to: dba
24 +
25 +template: exporting_metrics_lost
26 +families: *
27 + on: exporting_data_size
28 + units: metrics
29 + calc: abs($lost)
30 + every: 10s
31 + crit: ($this != 0) || ($status == $CRITICAL && abs($sent) == 0)
32 + delay: down 5m multiplier 1.5 max 1h
33 + info: number of metrics lost due to repeating failures to contact the external database server
34 + to: dba