Differences
This shows you the differences between two versions of the page.
|
tech:nagios:plugin_http_response_time [2018/05/03 06:27] |
tech:nagios:plugin_http_response_time [2018/05/03 06:27] (current) |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| + | ====== Nagios plugin - average response time for previous minute ====== | ||
| + | Obsoleted: Check [[plugin_http_metrics|Nagios HTTP Metrics]] | ||
| + | <code bash> | ||
| + | #!/bin/bash | ||
| + | # | ||
| + | # Average Apache response time | ||
| + | # Written by Senthil Nathan | ||
| + | # Last Modified: Dec 9th 2015 | ||
| + | # | ||
| + | # Usage: ./http_response_time -f access_log_file -w Count Warn -c Count Critical | ||
| + | # | ||
| + | # Description: Average response time in apache access log for the previous minute | ||
| + | # | ||
| + | # This plugin is to sum and computer the average response time for previous minute | ||
| + | # Assumes apache log time stamp of format "%d/%b/%Y:%H:%M" | ||
| + | # E.g. 08/Dec/2015:10:55:15 | ||
| + | # Assumes the time in microseconds is the 11th field delimited by space | ||
| + | # | ||
| + | # Output: | ||
| + | # | ||
| + | # Response time is OK/Warning/Critical|'Response Time'=xxxxxxus;nnnnnn;mmmmmm;0 | ||
| + | # | ||
| + | # Examples: | ||
| + | # | ||
| + | # Warn if response time is > 100000 micro seconds | ||
| + | # Critical if response time is > 150000 micro seconds | ||
| + | # http_response_time -f /opt/apache2/HTTPServer12/logs/rts1prd-app_access_log -w 100000 -c 150000 | ||
| + | # | ||
| + | # | ||
| + | |||
| + | PROGNAME=`/bin/basename $0` | ||
| + | PROGPATH=`echo $0 | sed -e 's,[\\/][^\\/][^\\/]*$,,'` | ||
| + | REVISION="1.0" | ||
| + | |||
| + | . $PROGPATH/utils.sh | ||
| + | |||
| + | check_root() | ||
| + | { | ||
| + | # make sure script is running as root | ||
| + | if [ `whoami` != root ]; then | ||
| + | echo "UNKNOWN: please make sure script is running as root" | ||
| + | exit $STATE_UNKNOWN | ||
| + | fi | ||
| + | } | ||
| + | |||
| + | print_usage() { | ||
| + | echo "Usage: $PROGNAME -f <access log file path> -w <warning response time> -c <critical response time>" | ||
| + | echo "Usage: $PROGNAME --help" | ||
| + | echo "Usage: $PROGNAME --version" | ||
| + | } | ||
| + | |||
| + | print_revision() { | ||
| + | echo "Program: $PROGNAME" | ||
| + | echo "Version: $REVISION" | ||
| + | } | ||
| + | |||
| + | print_help() { | ||
| + | print_revision | ||
| + | echo "" | ||
| + | print_usage | ||
| + | echo "" | ||
| + | echo "Check response time for the previous minute for Nagios" | ||
| + | echo "" | ||
| + | } | ||
| + | |||
| + | # Check user is root (not required) | ||
| + | #check_root | ||
| + | |||
| + | # Make sure the correct number of command line | ||
| + | # arguments have been supplied | ||
| + | |||
| + | if [ $# -lt 1 ]; then | ||
| + | print_usage | ||
| + | exit $STATE_UNKNOWN | ||
| + | fi | ||
| + | |||
| + | # Grab the command line arguments | ||
| + | |||
| + | exitstatus=$STATE_WARNING #default | ||
| + | while test -n "$1"; do | ||
| + | case "$1" in | ||
| + | --help) | ||
| + | print_help | ||
| + | exit $STATE_OK | ||
| + | ;; | ||
| + | -h) | ||
| + | print_help | ||
| + | exit $STATE_OK | ||
| + | ;; | ||
| + | --version) | ||
| + | print_revision | ||
| + | exit $STATE_OK | ||
| + | ;; | ||
| + | -V) | ||
| + | print_revision | ||
| + | exit $STATE_OK | ||
| + | ;; | ||
| + | --warning) | ||
| + | thewarn=$2 | ||
| + | shift | ||
| + | ;; | ||
| + | -w) | ||
| + | thewarn=$2 | ||
| + | shift | ||
| + | ;; | ||
| + | --critical) | ||
| + | thecrit=$2 | ||
| + | |||
| + | --critical) | ||
| + | thecrit=$2 | ||
| + | shift | ||
| + | ;; | ||
| + | -c) | ||
| + | thecrit=$2 | ||
| + | shift | ||
| + | ;; | ||
| + | -f) | ||
| + | thefile=$2 | ||
| + | shift | ||
| + | ;; | ||
| + | --filename) | ||
| + | thefile=$2 | ||
| + | shift | ||
| + | ;; | ||
| + | *) | ||
| + | echo "Unknown argument: $1" | ||
| + | print_usage | ||
| + | exit $STATE_UNKNOWN | ||
| + | ;; | ||
| + | esac | ||
| + | shift | ||
| + | done | ||
| + | |||
| + | # Validate arguments | ||
| + | if [ -z $thecrit ]; then | ||
| + | print_usage | ||
| + | exit $STATE_UNKNOWN | ||
| + | fi | ||
| + | if [ -z $thewarn ]; then | ||
| + | print_usage | ||
| + | exit $STATE_UNKNOWN | ||
| + | fi | ||
| + | if [ -z $thefile ]; then | ||
| + | print_usage | ||
| + | exit $STATE_UNKNOWN | ||
| + | fi | ||
| + | |||
| + | # Check begins here | ||
| + | |||
| + | # | ||
| + | declare -i responsetime | ||
| + | PMIN=`date --date '-1 min' +"%d/%b/%Y:%H:%M"` | ||
| + | responsetime=`grep $PMIN $thefile|awk '{ sum += $11; n++ } END { if (n > 0) printf("%d", sum / n); }'` | ||
| + | |||
| + | #if [ $? -eq 1 ]; then | ||
| + | # echo "Response Time Check Error" | ||
| + | # exit $STATE_UNKNOWN | ||
| + | #fi | ||
| + | # | ||
| + | if [ $responsetime -ge $thecrit ]; then | ||
| + | echo "Response Time is Critical|'Response Time'=${responsetime}us;${thewarn};${thecrit};0" | ||
| + | exit $STATE_CRITICAL | ||
| + | fi | ||
| + | if [ $responsetime -ge $thewarn ]; then | ||
| + | echo "Response Time is Warning|'Response Time'=${responsetime}us;${thewarn};${thecrit};0" | ||
| + | exit $STATE_WARNING | ||
| + | fi | ||
| + | if [ $responsetime -lt $thewarn ]; then | ||
| + | echo "Response Time is OK|'Response Time'=${responsetime}us;${thewarn};${thecrit};0" | ||
| + | exit $STATE_OK | ||
| + | fi | ||
| + | # | ||
| + | echo "Response time Check Unknown" | ||
| + | exit $STATE_UNKNOWN | ||
| + | |||
| + | </code> | ||
