Skip to content
Permalink
Browse files

7405 elasticsearch_indices: new check for monitoring of elasticsearch…

… indices

This check uses the datasource program "Check state of elasticsearch".

The document count and size growth per minute will be recorded and
averaged for a set amount of time (30 minutes by default). The last
recent document count growth and size growth will be compared to this
average value. You can set thresholds on how much higher the last recent
growth can be compared to the average growth.

Change-Id: I840d1651750d89c39a3cf21666d7e504333f0a1d
  • Loading branch information...
makanakoeln authored and Ronny Bruska committed Apr 4, 2019
1 parent 7ca740b commit d0dd5d4c22a1c7a105d5b2a8a0c3901d0ac721c3
@@ -0,0 +1,15 @@
Title: elasticsearch_indices: new check for monitoring of elasticsearch indices
Level: 1
Component: checks
Compatible: compat
Edition: cre
Version: 1.6.0i1
Date: 1554373898
Class: feature

This check uses the datasource program "Check state of elasticsearch". The
document count and size growth per minute will be recorded and averaged for a
set amount of time (30 minutes by default). The last recent document count
growth and size growth will be compared to this average value. You can set
thresholds on how much higher the last recent growth can be compared to the
average growth.
@@ -0,0 +1,18 @@
title: Elasticsearch: Indices
agents: elasticsearch
catalog: app/elasticsearch
license: GPL
distribution: check_mk
description:
This check uses the special agent for elasticsearch. The document count and
size growth per minute will be recorded and averaged for a set amount of time
(30 minutes by default). The last recent document count growth and size growth
will be compared to this average value. Thresholds can be set on how much higher
the last recent growth can be compared to the average growth.

inventory:
One check for each indice will be created

item:
The name of the index

@@ -0,0 +1,106 @@
#!/usr/bin/python
# -*- encoding: utf-8; py-indent-offset: 4 -*-
# +------------------------------------------------------------------+
# | ____ _ _ __ __ _ __ |
# | / ___| |__ ___ ___| | __ | \/ | |/ / |
# | | | | '_ \ / _ \/ __| |/ / | |\/| | ' / |
# | | |___| | | | __/ (__| < | | | | . \ |
# | \____|_| |_|\___|\___|_|\_\___|_| |_|_|\_\ |
# | |
# | Copyright Mathias Kettner 2019 mk@mathias-kettner.de |
# +------------------------------------------------------------------+
#
# This file is part of Check_MK.
# The official homepage is at http://mathias-kettner.de/check_mk.
#
# check_mk is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by
# the Free Software Foundation in version 2. check_mk is distributed
# in the hope that it will be useful, but WITHOUT ANY WARRANTY; with-
# out even the implied warranty of MERCHANTABILITY or FITNESS FOR A
# PARTICULAR PURPOSE. See the GNU General Public License for more de-
# tails. You should have received a copy of the GNU General Public
# License along with GNU Make; see the file COPYING. If not, write
# to the Free Software Foundation, Inc., 51 Franklin St, Fifth Floor,
# Boston, MA 02110-1301 USA.

# <<<elasticsearch_indices>>>
# filebeat-6.5.4 11492614 801366929

ElasticIndex = collections.namedtuple("ElasticIndex", [
"count",
"size",
])


def parse_elasticsearch_indices(info):
parsed = {}

for line in info:
try:
index, count, size = line
if parsed.get(index):
# sum up count/size for index names which already appeared
parsed[index] = parsed[index]._replace(count=parsed[index].count + int(count))
parsed[index] = parsed[index]._replace(size=parsed[index].size + int(size))
else:
parsed.setdefault(index, ElasticIndex(
int(count),
int(size),
))
except (IndexError, ValueError):
pass

return parsed


@get_parsed_item_data
def check_elasticsearch_indices(item, params, item_data):
for value, name, infotext, hr_func, unit in [
(item_data.count, "elasticsearch_count", "count", int, "docs"),
(item_data.size, "elasticsearch_size", "size", get_bytes_human_readable, ""),
]:

if params.get("%s_rate" % name):
avg = params.get("%s_rate" % name)[2]
else:
avg = 30

yield check_levels(
value,
name, (None, None),
human_readable_func=hr_func,
unit=unit,
infoname="Total %s" % infotext)

this_time = time.time()
rate = get_rate("elasticsearch_indices.%s.%s" % (name, item), this_time, value) * 60

avg_rate = get_average("elasticsearch_indices.%s.%s.avg" % (name, item), this_time, rate,
avg)

if params.get("%s_rate" % name):
warn, crit, avg = params["%s_rate" % name]
avg_rate_warn = (avg_rate * (warn / 100 + 1))
avg_rate_crit = (avg_rate * (crit / 100 + 1))
params_avg = (avg_rate_warn, avg_rate_crit)
else:
params_avg = (None, None)

yield check_levels(
rate,
"%s_rate" % name,
params_avg,
human_readable_func=hr_func,
unit="%s per Minute" % unit,
infoname="Average %s" % infotext)


check_info["elasticsearch_indices"] = {
"check_function": check_elasticsearch_indices,
"parse_function": parse_elasticsearch_indices,
"inventory_function": discover(),
"service_description": "Elasticsearch Indice %s",
"has_perfdata": True,
"group": "elasticsearch_indices",
}
@@ -5757,6 +5757,156 @@ def register_fireye_metrics():
"color": "22/a",
}

metric_info["elasticsearch_size_avg"] = {
"title": _("Average size growth"),
"unit": "bytes",
"color": "33/a",
}

metric_info["elasticsearch_size_rate"] = {
"title": _("Size growth per minute"),
"unit": "bytes",
"color": "31/a",
}

metric_info["elasticsearch_size"] = {
"title": _("Total size"),
"unit": "bytes",
"color": "31/b",
}

metric_info["elasticsearch_count_avg"] = {
"title": _("Average document count growth"),
"unit": "count",
"color": "45/a",
}

metric_info["elasticsearch_count_rate"] = {
"title": _("Document count growth per minute"),
"unit": "count",
"color": "43/a",
}

metric_info["elasticsearch_count"] = {
"title": _("Total documents"),
"unit": "count",
"color": "43/b",
}

metric_info["active_primary_shards"] = {
"title": _("Active primary shards"),
"unit": "count",
"color": "21/b",
}

metric_info["active_shards"] = {
"title": _("Active shards"),
"unit": "count",
"color": "21/a",
}

metric_info["active_shards_percent_as_number"] = {
"title": _("Active shards in percent"),
"unit": "%",
"color": "22/a",
}

metric_info["number_of_data_nodes"] = {
"title": _("Data nodes"),
"unit": "count",
"color": "41/a",
}

metric_info["delayed_unassigned_shards"] = {
"title": _("Delayed unassigned shards"),
"unit": "count",
"color": "42/a",
}

metric_info["initializing_shards"] = {
"title": _("Initializing shards"),
"unit": "count",
"color": "52/a",
}

metric_info["number_of_nodes"] = {
"title": _("Nodes"),
"unit": "count",
"color": "43/a",
}

metric_info["number_of_pending_tasks"] = {
"title": _("Pending tasks"),
"unit": "count",
"color": "53/a",
}

metric_info["number_of_pending_tasks_rate"] = {
"title": _("Pending tasks delta"),
"unit": "count",
"color": "14/b",
}

metric_info["number_of_pending_tasks_avg"] = {
"title": _("Average pending tasks delta"),
"unit": "count",
"color": "26/a",
}

metric_info["relocating_shards"] = {
"title": _("Relocating shards"),
"unit": "count",
"color": "16/b",
}

metric_info["task_max_waiting_in_queue_millis"] = {
"title": _("Maximum wait time of all tasks in queue"),
"unit": "count",
"color": "11/a",
}

metric_info["unassigned_shards"] = {
"title": _("Unassigned shards"),
"unit": "count",
"color": "14/a",
}

metric_info["number_of_in_flight_fetch"] = {
"title": _("Ongoing shard info requests"),
"unit": "count",
"color": "31/a",
}

metric_info["open_file_descriptors"] = {
"title": _("Open file descriptors"),
"unit": "count",
"color": "14/a",
}

metric_info["max_file_descriptors"] = {
"title": _("Max file descriptors"),
"unit": "count",
"color": "11/a",
}

metric_info["cpu_percent"] = {
"title": _("CPU used"),
"unit": "%",
"color": "16/a",
}

metric_info["cpu_total_in_millis"] = {
"title": _("CPU total in ms"),
"unit": "1/s",
"color": "26/a",
}

metric_info["mem_total_virtual_in_bytes"] = {
"title": _("Total virtual memory"),
"unit": "bytes",
"color": "53/a",
}

#.
# .--Checks--------------------------------------------------------------.
# | ____ _ _ |
@@ -9235,6 +9385,42 @@ def get_skype_mobile_perfometer_segments():
"color": "16/a",
})

perfometer_info.append(("stacked", [{
"type": "logarithmic",
"metric": "elasticsearch_size_rate",
"half_value": 5000,
"exponent": 2,
}, {
"type": "logarithmic",
"metric": "elasticsearch_count_rate",
"half_value": 10,
"exponent": 2,
}]))

perfometer_info.append({
"type": "logarithmic",
"metric": "number_of_pending_tasks_rate",
"half_value": 10,
"exponent": 2,
"unit": "count",
})

perfometer_info.append(("dual", [{
"type": "linear",
"segments": ["active_primary_shards"],
"total": "active_shards",
}, {
"type": "linear",
"segments": ["active_shards"],
"total": "active_shards",
}]))

perfometer_info.append({
"type": "linear",
"segments": ["active_shards_percent_as_number"],
"total": 100.0,
})

#.
# .--Graphs--------------------------------------------------------------.
# | ____ _ |
@@ -11107,3 +11293,11 @@ def get_skype_mobile_metrics():
("number_of_data_nodes", "area"),
],
}

graph_info["active_shards"] = {
"title": _("Active shards"),
"metrics": [
("active_shards", "area"),
("active_primary_shards", "area"),
],
}

0 comments on commit d0dd5d4

Please sign in to comment.
You can’t perform that action at this time.