Build precise queries to find exactly what you need
Press ESC to close
@EndlessTundra
Favorites0
Views0
Projects1
Hey Everyone, this script was very nice but it also had some weird irritations so I reworked it and added: - Allow empty Warning/Critical values - Added Modes so that you can check Disk IOs, Disk Queue, or Disk Wait Times - To see the usage information use check_diskio.sh -h Sorry I don't have this anywhere on the web so I'm just going to paste it here: #!/bin/bash # # Version 0.0.2 - Jan/2009 # Changes: added device verification # # by Thiago Varela - [email protected] # # -------------------------------------- # # Version 0.0.3 - Dec/2011 # Changes: # - changed values from bytes to mbytes # - fixed bug to get traffic data without comma but point # - current values are displayed now, not average values (first run of iostat) # # by Philipp Niedziela - [email protected] # # Version 0.0.4 - April/2014 # Changes: # - Allow Empty warn/crit levels # - Can check I/O, WAIT Time, or Queue # # by Warren Turner iostat=`which iostat 2>/dev/null` bc=`which bc 2>/dev/null` function help { echo -e " Usage: -d = --Device to be checked. Example: "-d sda" -i = IO Check Mode --Checks Total Disk IO, Read IO/Sec, Write IO/Sec, Bytes Read/Sec, Bytes Written/Sec --warning/critical = Total IO,Read IO/Sec,Write IO/Sec,Bytes Read/Sec,Bytes Written/Sec -q = Queue Mode --Checks Disk Queue Lengths --warning/critial = Total Queue Length,Read Queue Length,Write Queue Length -W = Wait Time Mode --Check the time for I/O requests issued to the device to be served. This includes the time spent by the requests in queue and the time spent servicing them. --warning/critical = Avg I/O Wait Time/ms,Read Wait Time/ms,Write Wait Time/ms " exit -1 } # Ensuring we have the needed tools: ( [ ! -f $iostat ] || [ ! -f $bc ] ) && ( echo "ERROR: You must have iostat and bc installed in order to run this pluginntuse: apt-get install systat bcn" && exit -1 ) io=0 queue=0 waittime=0 msg="OK" # Getting parameters: while getopts "d:w:c:io:qu:Wt:h" OPT; do case $OPT in "d") disk=$OPTARG;; "w") warning=$OPTARG;; "c") critical=$OPTARG;; "i") io=1;; "q") queue=1;; "W") waittime=1;; "h") help;; esac done # Autofill if parameters are empty if [ -z "$disk" ] then disk=sda fi if [ -z "$warning" ] then warning=99999 fi if [ -z "$critical" ] then critical=99999 fi # Adjusting the warn and crit levels: crit_total=`echo $critical | cut -d, -f1` crit_read=`echo $critical | cut -d, -f2` crit_written=`echo $critical | cut -d, -f3` crit_kbytes_read=`echo $critical | cut -d, -f4` crit_kbytes_written=`echo $critical | cut -d, -f5` warn_total=`echo $warning | cut -d, -f1` warn_read=`echo $warning | cut -d, -f2` warn_written=`echo $warning | cut -d, -f3` warn_kbytes_read=`echo $warning | cut -d, -f4` warn_kbytes_written=`echo $warning | cut -d, -f5` # # Checking parameters: # [ ! -b "/dev/$disk" ] && echo "ERROR: Device incorrectly specified" && help # ( [ "$warn_total" == "" ] || [ "$warn_read" == "" ] || [ "$warn_written" == "" ] || # [ "$crit_total" == "" ] || [ "$crit_read" == "" ] || [ "$crit_written" == "" ] ) && # echo "ERROR: You must specify all warning and critical levels" && help # ( [[ "$warn_total" -ge "$crit_total" ]] || # [[ "$warn_read" -ge "$crit_read" ]] || # [[ "$warn_written" -ge "$crit_written" ]] ) && # echo "ERROR: critical levels must be highter than warning levels" && help # iostat parameters: # -m: megabytes # -k: kilobytes # first run of iostat shows statistics since last reboot, second one shows current vaules of hdd # Doing the actual checks: ## IO Check ## if [ "$io" == "1" ] then total=`$iostat $disk -y -k -d 2 1 | grep $disk | awk '{print $2}'` read_sec=`$iostat $disk -x -y -k -d 2 1 | grep $disk | awk '{print $4}'` written_sec=`$iostat $disk -x -y -k -d 2 1 | grep $disk | awk '{print $5}'` kbytes_read_sec=`$iostat $disk -x -y -k -d 2 1 | grep $disk | awk '{print $6}'` kbytes_written_sec=`$iostat $disk -x -y -k -d 2 1 | grep $disk | awk '{print $7}'` # IO # "Converting" values to float (string replace , with .) total=${total/,/.} read_sec=${read_sec/,/.} written_sec=${written_sec/,/.} kbytes_read_sec=${kbytes_read_sec/,/.} kbytes_written_sec=${kbytes_written_sec/,/.} # IO # Comparing the result and setting the correct level: if [ "$warn_total" -ne "99999" ] then if ( [ "`echo "$total >= $warn_total" | bc`" == "1" ] || [ "`echo "$read_sec >= $warn_read" | bc`" == "1" ] || [ "`echo "$written_sec >= $warn_written" | bc`" == "1" ] || [ "`echo "$kbytes_read_sec >= $warn_kbytes_read" | bc -q`" == "1" ] || [ "`echo "$kbytes_written_sec >= $warn_kybtes_written" | bc`" == "1" ] ) then msg="WARNING" status=1 fi fi if [ "$crit_total" -ne "99999" ] then if ( [ "`echo "$total >= $crit_total" | bc`" == "1" ] || [ "`echo "$read_sec >= $crit_read" | bc -q`" == "1" ] || [ "`echo "$written_sec >= $crit_written" | bc`" == "1" ] || [ "`echo "$kbytes_read_sec >= $crit_kbytes_read" | bc -q`" == "1" ] || [ "`echo "$kbytes_written_sec >= $crit_kbytes_written" | bc`" == "1" ] ) then msg="CRITICAL" status=2 fi fi if [ "$crit_total" == "99999" ] && [ "$warn_total" == "99999" ] then msg="OK" status=0 fi # IO # Printing the results: echo "$msg - I/O stats: Total IO/Sec=$total Read IO/Sec=$read_sec Write IO/Sec=$written_sec KBytes Read/Sec=$kbytes_read_sec KBytes_Written/Sec=$kbytes_written_sec | 'Total IO/Sec'=$total; 'Read IO/Sec'=$read_sec; 'Write IO/Sec'=$written_sec; 'KBytes Read/Sec'=$kbytes_read_sec; 'KKBytes_Written/Sec'=$kbytes_written_sec;" fi ## QUEUE Check ## if [ "$queue" == "1" ] then total=`$iostat $disk -x -y -k -d 2 1 | grep $disk | awk '{print $8}'` read_sec=`$iostat $disk -x -y -k -d 2 1 | grep $disk | awk '{print $2}'` written_sec=`$iostat $disk -x -y -k -d 2 1 | grep $disk | awk '{print $3}'` # QUEUE # "Converting" values to float (string replace , with .) total=${total/,/.} read_sec=${read_sec/,/.} written_sec=${written_sec/,/.} # QUEUE # Comparing the result and setting the correct level: if [ "$warn_total" -ne "99999" ] then if ( [ "`echo "$total >= $warn_total" | bc`" == "1" ] || [ "`echo "$read_sec >= $warn_read" | bc`" == "1" ] || [ "`echo "$written_sec >= $warn_written" | bc`" == "1" ] ) then msg="WARNING" status=1 fi fi if [ "$crit_total" -ne "99999" ] then if ( [ "`echo "$total >= $crit_total" | bc`" == "1" ] || [ "`echo "$read_sec >= $crit_read" | bc -q`" == "1" ] || [ "`echo "$written_sec >= $crit_written" | bc`" == "1" ] ) then msg="CRITICAL" status=2 fi fi if [ "$crit_total" == "99999" ] && [ "$warn_total" == "99999" ] then msg="OK" status=0 fi # QUEUE # Printing the results: echo "$msg - Disk Queue Stats: Average Queue Length=$total Read Queue/Sec=$read_sec Write Queue/Sec=$written_sec | 'total'=$total; 'Read Queue/Sec'=$read_sec; 'Write Queue/Sec'=$written_sec;" fi ## WAIT TIME Check ## if [ "$waittime" == "1" ] then total=`$iostat $disk -x -y -k -d 2 1 | grep $disk | awk '{print $10}'` read_sec=`$iostat $disk -x -y -k -d 2 1 | grep $disk | awk '{print $11}'` written_sec=`$iostat $disk -x -y -k -d 2 1 | grep $disk | awk '{print $12}'` # QUEUE # "Converting" values to float (string replace , with .) total=${total/,/.} read_sec=${read_sec/,/.} written_sec=${written_sec/,/.} # WAIT TIME # Comparing the result and setting the correct level: if [ "$warn_total" -ne "99999" ] then if ( [ "`echo "$total >= $warn_total" | bc`" == "1" ] || [ "`echo "$read_sec >= $warn_read" | bc`" == "1" ] || [ "`echo "$written_sec >= $warn_written" | bc`" == "1" ] ) then msg="WARNING" status=1 fi fi if [ "$crit_total" -ne "99999" ] then if ( [ "`echo "$total >= $crit_total" | bc`" == "1" ] || [ "`echo "$read_sec >= $crit_read" | bc -q`" == "1" ] || [ "`echo "$written_sec >= $crit_written" | bc`" == "1" ] ) then msg="CRITICAL" status=2 fi fi if [ "$crit_total" == "99999" ] && [ "$warn_total" == "99999" ] then msg="OK" status=0 fi # WAIT TIME # Printing the results: echo "$msg - Wait Time Stats: Avg I/O Wait Time/ms=$total Avg Read Wait Time/ms=$read_sec Avg Write Wait Time/ms=$written_sec | 'Avg I/O Wait Time/ms'=$total; 'Avg Read Wait Time/ms'=$read_sec; 'Avg Write Wait Time/ms'=$written_sec;" fi exit $status
Reviewed 11 years ago
I tried to compile this on Ubuntu 14.04 and got an error, anybody know how to fix it? ./configure --with-ssl=/usr/bin/openssl --with-ssl-lib=/usr/lib/x86_64-linux-gnu --prefix=/etc/nagios3 --enable-command-args make all gcc -g -O2 -I/usr/include/openssl -DHAVE_CONFIG_H -I ../include -I ./../include -o nrpe ./nrpe.c ./utils.c ./acl.c -L/usr/lib/x86_64-linux-gnu -lssl -lcrypto -lnsl ./nrpe.c: In function ‘init_ssl’: ./nrpe.c:319:9: warning: format ‘%s’ expects argument of type ‘char *’, but argument 4 has type ‘int’ [-Wformat=] sslprm.cert_file, ERR_error_string(x, NULL)); ^ ./nrpe.c: In function ‘handle_conn_ssl’: ./nrpe.c:1754:9: warning: format ‘%s’ expects argument of type ‘char *’, but argument 4 has type ‘int’ [-Wformat=] remote_host, ERR_reason_error_string(x)); ^ ./nrpe.c: In function ‘main’: ./nrpe.c:168:9: warning: ignoring return value of ‘getcwd’, declared with attribute warn_unused_result [-Wunused-result] getcwd(config_file, sizeof(config_file)); ^ ./nrpe.c: In function ‘set_stdio_sigs’: ./nrpe.c:553:7: warning: ignoring return value of ‘chdir’, declared with attribute warn_unused_result [-Wunused-result] chdir("/"); ^ ./nrpe.c: In function ‘my_system’: ./nrpe.c:1994:6: warning: ignoring return value of ‘pipe’, declared with attribute warn_unused_result [-Wunused-result] pipe(fd); /* create a pipe */ ^ In file included from ./nrpe.c:27:0: ../include/config.h:110:28: warning: ignoring return value of ‘seteuid’, declared with attribute warn_unused_result [-Wunused-result] #define SETEUID(id) seteuid(id) ^ ./nrpe.c:2026:3: note: in expansion of macro ‘SETEUID’ SETEUID(0); /* get root back so the next call works correctly */ ^ ./nrpe.c:2050:9: warning: ignoring return value of ‘write’, declared with attribute warn_unused_result [-Wunused-result] write(fd[1], buffer, strlen(buffer) + 1); ^ ./nrpe.c:2058:10: warning: ignoring return value of ‘write’, declared with attribute warn_unused_result [-Wunused-result] write(fd[1], buffer, bytes_read); ^ ./nrpe.c:2061:9: warning: ignoring return value of ‘write’, declared with attribute warn_unused_result [-Wunused-result] write(fd[1], "", 1); ^ ./nrpe.c: In function ‘write_pid_file’: ./nrpe.c:2267:8: warning: ignoring return value of ‘write’, declared with attribute warn_unused_result [-Wunused-result] write(fd, pbuf, strlen(pbuf)); ^ In file included from ./nrpe.c:27:0: ./nrpe.c: In function ‘remove_pid_file’: ../include/config.h:110:28: warning: ignoring return value of ‘seteuid’, declared with attribute warn_unused_result [-Wunused-result] #define SETEUID(id) seteuid(id) ^ ./nrpe.c:2286:2: note: in expansion of macro ‘SETEUID’ SETEUID(0); /* get root back so we can delete the pid file */ ^ gcc -g -O2 -I/usr/include/openssl -DHAVE_CONFIG_H -I ../include -I ./../include -o check_nrpe ./check_nrpe.c ./utils.c -L/usr/lib/x86_64-linux-gnu -lssl -lcrypto -lnsl ./check_nrpe.c: In function ‘connect_to_remote’: ./check_nrpe.c:926:9: warning: format ‘%s’ expects argument of type ‘char *’, but argument 4 has type ‘int’ [-Wformat=] rem_host, ERR_reason_error_string(x)); ^ ./check_nrpe.c: In function ‘alarm_handler’: ./check_nrpe.c:1457:7: warning: ignoring return value of ‘write’, declared with attribute warn_unused_result [-Wunused-result] write(STDOUT_FILENO, msg1, sizeof(msg1) - 1); ^ ./check_nrpe.c:1458:7: warning: ignoring return value of ‘write’, declared with attribute warn_unused_result [-Wunused-result] write(STDOUT_FILENO, text, lth1); ^ ./check_nrpe.c:1459:7: warning: ignoring return value of ‘write’, declared with attribute warn_unused_result [-Wunused-result] write(STDOUT_FILENO, msg2, sizeof(msg2) - 1); ^ ./check_nrpe.c:1460:7: warning: ignoring return value of ‘write’, declared with attribute warn_unused_result [-Wunused-result] write(STDOUT_FILENO, timeout_txt, lth2); ^ ./check_nrpe.c:1461:7: warning: ignoring return value of ‘write’, declared with attribute warn_unused_result [-Wunused-result] write(STDOUT_FILENO, msg3, sizeof(msg3) - 1);
Reviewed 9 years ago