Merge branch 'update-docs' into 'master'

Update docs

See merge request !121

check_ceph_status

@@ -19,12 +19,15 @@
 # 2021-03-31  v1.2  <axel.hahn@iml.unibe.ch>  estimate remaining time of ceph recovery
 # 2021-04-12  v1.3  <axel.hahn@iml.unibe.ch>  if degraded items are 0 delete init file too
 # 2023-04-24  v1.4  <axel.hahn@unibe.ch>      update for newer ceph versions
+# 2023-06-19  v1.5  <axel.hahn@unibe.ch>      add help and param support; no more tmpfile
 # ======================================================================
 
 . $(dirname $0)/inc_pluginfunctions
 
-initfile=/tmp/ceph-status-not-ok-start
-tmpfile=/tmp/ceph-status.out_$$
+initfile="/tmp/ceph-status-not-ok-start-$USER"
+
+self_APPNAME=$( basename $0 | tr [:lower:] [:upper:] )
+self_APPVERSION=1.5
 
 iSleep=3
 doLoop=1
@@ -39,24 +42,52 @@ line="__________________________________________________________________________
 # FUNCTIONS
 # ----------------------------------------------------------------------
 
+function showHelp(){
+    _self=$(basename $0)
+cat <<EOF
+______________________________________________________________________
+
+$self_APPNAME 
+v$self_APPVERSION
+
+(c) Institute for Medical Education - University of Bern
+Licence: GNU GPL 3
+______________________________________________________________________
+
+Show ceph health status.
+The state of the check switches to warning if HEALTH_WARN was detected
+and is error of other HEALTH values than HEALTH_WARN or HEALTH_OK.
+
+In the output is the complete output of the command "ceph status".
+
+If degraded objects are found it shows the progress of repair process.
+
+SYNTAX:
+$_self
+
+OPTIONS:
+    -h or --help   show this help.
+
+EOF
+}
+
 function readCephStatus(){
-        sudo ceph status >$tmpfile
-        if [ $? -ne 0 ]; then
-                rm -f $tmpfile
+        if ! data=$( sudo /bin/ceph status 2>&1 ); then
+                echo "$data"
                 ph.abort "UNKNOWN: ceph is not available or no sudo permissions to execute ceph commands."
         fi
 }
 function getCephStatus(){
-        cat $tmpfile | grep "health:" | awk '{ print $2 }' 
+        grep "health:" <<< "$data" | awk '{ print $2 }' 
 }
 function getTotalObjects(){
-        cat $tmpfile | grep "pgs:.*objects degraded" | awk '{ print $2 }' | cut -f 2 -d "/"
+        grep "pgs:.*objects degraded"  <<< "$data" | awk '{ print $2 }' | cut -f 2 -d "/"
 }
 function getDegraded(){
-        cat $tmpfile | grep "pgs:.*objects degraded" | awk '{ print $2 }' | cut -f 1 -d "/"
+        grep "pgs:.*objects degraded"  <<< "$data" | awk '{ print $2 }' | cut -f 1 -d "/"
 }
 function getMisplaced(){
-        cat $tmpfile | grep ".*objects misplaced" | awk '{ print $2 }' | cut -f 1 -d "/"
+        grep ".*objects misplaced"     <<< "$data" | awk '{ print $2 }' | cut -f 1 -d "/"
 }
 
 
@@ -64,6 +95,14 @@ function getMisplaced(){
 # MAIN
 # ----------------------------------------------------------------------
 
+# --- check param -h
+case "$1" in
+    "--help"|"-h")
+        showHelp
+        exit 0
+        ;;
+    *)
+esac
 
 readCephStatus
 if [ ! -f $initfile ]; then
@@ -95,11 +134,11 @@ fi
 ph.status "Ceph status is $sCephStatus"
 echo
 
-while [ ! "$sCephStatus" = "HEALTH_OK" -a $doLoop = 1 ]; do
+while [ ! "$sCephStatus" = "HEALTH_OK" ] && [ $doLoop = 1 ]; do
 
         typeset -i iObjCount=$iDeg+$iMis
 
-        iTsNow=`date +%s`
+        iTsNow=$( date +%s )
 
         typeset -i iDegNow=$(getDegraded)
         typeset -i iMisNow=$(getMisplaced)
@@ -114,7 +153,7 @@ while [ ! "$sCephStatus" = "HEALTH_OK" -a $doLoop = 1 ]; do
         # typeset -i iDeltaMis2=$iLastMis-$iMisNow
 
 
-        if [ $iTsDelta -gt 0 ]; then
+        if [ $iDegNow+$iMisNow -gt 0 ]  && [ $iTsDelta -gt 0 ]; then
                 typeset -i iDegPerMin=$iDoneDeg/$iTsDelta*60
                 if [ $iDegPerMin -gt 0 ]; then
                         # timeByDeg=`echo $iTsDelta*$iObjCount/$iDoneDeg/60 - $iTsDelta/60 | bc`
@@ -180,9 +219,7 @@ while [ ! "$sCephStatus" = "HEALTH_OK" -a $doLoop = 1 ]; do
         printf "misplaced  $tbl" "$iMis"     "$iMisNow" "$iDoneMis"   "$iMisPerMin" "$_timeByMis"
         printf "total      $tbl" $iObjCount  $iNowTotal  $iDoneTotal  " "           "$sTimeLeft"
         echo $line
-        cat $tmpfile
-        rm -f $tmpfile 2>/dev/null
-
+        echo "$data"
 
         if [ $doSingleLoop = 1 ]; then
                 doLoop=0
@@ -194,12 +231,10 @@ while [ ! "$sCephStatus" = "HEALTH_OK" -a $doLoop = 1 ]; do
 
 done
 
-test $doSingleLoop = 0 -o "$sCephStatus" = "HEALTH_OK" && cat $tmpfile
+test $doSingleLoop = 0 -o "$sCephStatus" = "HEALTH_OK" && echo "$data"
 echo
-echo --- DONE `date`
+echo --- DONE $( date )
 test "$sCephStatus" = "HEALTH_OK" && rm -f $initfile 2>/dev/null
 test $iDeg -eq 0 && rm -f $initfile 2>/dev/null
-rm -f $tmpfile 2>/dev/null
-
 
 ph.exit

docs/20_Checks/_index.md

@@ -12,7 +12,7 @@ There is one include script used by all checks:
 * [check_ceph_diskfree](check_ceph_diskfree.md)
 * [check_ceph_io](check_ceph_io.md)
 * [check_ceph_osd](check_ceph_osd.md)
-* check_ceph_status
+* [check_ceph_status](check_ceph_status.md)
 * check_clientbackup
 * check_couchdb-lb
 * [check_cpu](check_cpu.md)
@@ -23,22 +23,28 @@ There is one include script used by all checks:
 * check_haproxy_health
 * check_haproxy_status
 * check_memory
+* check_mysqlserver
 * check_netio
 * [check_netstat](check_netstat.md)
 * [check_onehost](check_onehost.md)
 * [check_onevm](check_onevm.md)
 * check_opencpu
 * check_packages2install
+* check_php-fpm-status
 * check_proc_mem
 * check_proc_ressources
 * check_proc_zombie
 * [check_psqlserver](check_psqlserver.md)
 * [check_reboot_required](check_reboot_required.md)
+* check_requirements
 * check_sensuplugins
 * check_smartstatus
 * [check_snmp_data](check_snmp_data.md)
+* check_snmp_printer
+* check_snmp_switch
 * [check_snmp_synology](check_snmp_synology.md)
 * check_ssl
+* check_ssl_certs
 * check_systemdservices
 * check_timesync
 * check_uptime

docs/20_Checks/check_ceph_diskfree.md

-# check Ceph diskfree
+# Check Ceph diskfree
 
 ## Introduction
 
@@ -61,4 +61,4 @@ OK         .mgr   1    1   18 MiB        6   18 MiB      0     16 TiB
 OK         one    2   32  255 GiB   66.65k  255 GiB   0.50     16 TiB
 OK         two    3   32      0 B        0      0 B      0     25 TiB
  |global-total=59373627899904;;;0;59373627899904 global-avail=58274116272128;;;0;59373627899904 global-used=823559979008;;;0;59373627899904 
-...
+```

docs/20_Checks/check_ceph_io.md

-# check Ceph IO
+# Check Ceph IO
 
 ## Introduction
 
@@ -55,4 +55,4 @@ check_ceph_io -t "   client: 255 B/s rd, 0 op/s rd, 0 op/s wr"
 ```txt
 OK:    13 KiB/s rd, 1.1 MiB/s wr, 130 op/s rd, 137 op/s wr
 |cephio-read=13K;; cephio-write=1.1M;;
-...
+```

docs/20_Checks/check_ceph_osd.md

@@ -92,4 +92,4 @@ ID   CLASS  WEIGHT    TYPE NAME        STATUS  REWEIGHT  PRI-AFF
  22    ssd   1.74660          osd.22       up   1.00000  1.00000
  28    ssd   1.74660          osd.28       up   1.00000  1.00000
  |osd-total=30;;;0;30 osd-up=30;;;0;30 osd-down=0;;;0;30
-...
+```

docs/20_Checks/check_ceph_status.md

+# Check Ceph Status
+
+## Introduction
+
+**check_ceph_sttaus** is a plugin to show ceph status.
+It switches the state in dependency of the HEALTH_* value.
+
+## Requirements
+
+* `ceph` binary and sudo permission on it to get the information
+
+## Syntax
+
+```txt
+______________________________________________________________________
+
+DEV_CHECK_CEPH_STATUS 
+v1.5
+
+(c) Institute for Medical Education - University of Bern
+Licence: GNU GPL 3
+______________________________________________________________________
+
+Show ceph health status.
+The state of the check switches to warning if HEALTH_WARN was detected
+and is error of other HEALTH values than HEALTH_WARN or HEALTH_OK.
+
+In the output is the complete output of the command "ceph status".
+
+SYNTAX:
+check_ceph_status
+
+OPTIONS:
+    -h or --help   show this help.
+
+```
+
+### Parameters
+
+(none)
+
+## Examples
+
+`$ check_ceph_status` returns
+
+```txt
+OK: Ceph status is HEALTH_OK
+
+  cluster:
+    id:     12345678-68e3-4c21-bf95-4b5f802f81a4
+    health: HEALTH_OK
+ 
+  services:
+    mon: 3 daemons, quorum cephmon1,cephmon2,cephmon3 (age 2w)
+    mgr: cephmon3(active, since 2w), standbys: cephmon2, cephmon1
+    osd: 30 osds: 30 up (since 2w), 30 in (since 5w)
+ 
+  data:
+    pools:   3 pools, 161 pgs
+    objects: 608.44k objects, 2.3 TiB
+    usage:   6.9 TiB used, 47 TiB / 54 TiB avail
+    pgs:     161 active+clean
+ 
+  io:
+    client:   896 KiB/s rd, 12 MiB/s wr, 372 op/s rd, 401 op/s wr
+
+```
\ No newline at end of file

readme.md

@@ -8,51 +8,10 @@ This is a collection of our checks. They are used on Linux systems (Debian, Cent
 
 We use Icinga graphite module to show performance data. The templates are located in a sister repository
 
-
 📃 Sources:
 
 * Checks: <https://git-repo.iml.unibe.ch/iml-open-source/icinga-checks>
 * Graphs (Graphite): <https://git-repo.iml.unibe.ch/iml-open-source/icinga-graphite-templates>
 
-📗 Docs: see [./docs/](./docs) folder \
-📜 Licence: GNU GPL 3.0
-
-## Scripts
-
-There is one include script used by all checks:
-[inc_pluginfunctions](inc_pluginfunctions.md)
-
-## Checks
-
-* check_apache_requests
-* check_backup_one
-* check_ceph_diskfree
-* check_ceph_osd
-* check_ceph_status
-* check_clientbackup
-* check_couchdb-lb
-* check_cpu
-* check_cronstatus
-* check_disk-io
-* check_dns_responsetime
-* [check_eol](check_eol.md)
-* check_haproxy_health
-* check_haproxy_status
-* check_memory
-* check_netio
-* check_netstat
-* check_opencpu
-* check_packages2install
-* check_proc_mem
-* check_proc_ressources
-* check_proc_zombie
-* check_reboot_required
-* check_sensuplugins
-* check_smartstatus
-* [check_snmp_data](check_snmp_data.md)
-* check_snmp_synology
-* check_ssl
-* check_systemdservices
-* check_timesync
-* check_uptime
-* hello
+📜 Licence: GNU GPL 3.0 \
+📗 Docs: see <https://os-docs.iml.unibe.ch/icinga-checks/> or [./docs/](./docs) folder