1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
|
#!/usr/bin/python
#
# check_cluster_vol_usage
# Aggregated cluster capacity utilization for a
# gluster cluster
# The plugin reads status data using mk-livestatus
# Assumptions:
# - Volume utilization service names begin with "Volume-"
# - Host name associated is cluster name
# - All volume utilization output is of form
# "used=<val>;warn;crit;min;max"
#
# Copyright (C) 2014 Red Hat Inc
#
# This program 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; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
#
import sys
import re
from argparse import ArgumentParser
import livestatus
from glusternagios import utils
def checkVolumePerfData(clusterName):
# Write command to socket
cmd = "GET services\nColumns: description host_name " \
"perf_data custom_variables\nFilter: " \
"description ~~ %s" % 'Volume Utilization -'
table = livestatus.readLiveStatus(cmd)
totalUsed = 0.0
totalAvail = 0.0
for row in table:
if len(row) <= 3:
return 0.0, 0.0
host = row[1]
perf_data = row[2]
if len(perf_data) > 2:
perf_arr = perf_data.split(' ')
used = perf_arr[2].split('=')[1]
avail = perf_arr[1].split('=')[1]
if host == clusterName:
totalUsed += float(re.match(r'\d*\.?\d+', used).group())
totalAvail += float(re.match(r'\d*\.?\d+', avail).group())
return totalUsed, totalAvail
# Main method
if __name__ == "__main__":
parser = ArgumentParser(description="Calculate the aggregate "
"capacity usage in cluster")
parser.add_argument('-w', '--warning',
action='store',
type=int,
dest='warn',
help='Warning in %%',
default=70)
parser.add_argument('-c', '--critical',
action='store',
type=int,
dest='crit',
help='Critical threshold Warning in %%',
default=95)
parser.add_argument('-hg', '--host-group',
action='store',
type=str,
dest='hostgroup',
help='Name of cluster or hostgroup',
required=True)
args = parser.parse_args()
# Check the various performance statuses for the host
used, avail = checkVolumePerfData(args.hostgroup)
statusstr = utils.PluginStatus.OK
exitstatus = utils.PluginStatusCode.OK
if used == 0 and avail == 0:
statusstr = utils.PluginStatus.UNKNOWN
exitstatus = utils.PluginStatusCode.UNKNOWN
print ("%s - No volumes found" % statusstr)
else:
warn = int((args.warn * avail) / 100.0)
crit = int((args.crit * avail) / 100.0)
usedpercent = int((used / avail) * 100.0)
if (usedpercent >= args.warn):
statusstr = utils.PluginStatus.WARNING
exitstatus = utils.PluginStatusCode.WARNING
if (usedpercent >= args.crit):
statusstr = utils.PluginStatus.CRITICAL
exitstatus = utils.PluginStatusCode.CRITICAL
availGB = utils.convertSize(avail, "KB", "GB")
print ("%s - used %s%% of available %s GB|used=%s;%s;%s;0;%s;"
% (statusstr, usedpercent,
availGB, usedpercent, args.warn, args.crit, 100))
sys.exit(exitstatus)
|