Add check-md.sh script to monitor RAID device status

This commit adds a new bash script called check-md.sh that can be used to monitor the status of a RAID device. The script takes in options for warning and critical events, and checks the status of the specified MD-device. It then returns an exit code based on whether any warning or critical events were triggered, along with a message describing the current state of the array.
2023-06-01 14:34:36 +02:00 · 2023-06-01 14:34:36 +02:00 · b2fccadfa1
commit b2fccadfa1
parent 253e922f99
1 changed files with 124 additions and 0 deletions
--- a/check-md.sh
+++ b/check-md.sh
@ -0,0 +1,124 @@
+#!/bin/bash
+
+#
+#/
+#/ Usage:
+#/ check-md.sh --warning=<events> --critical=<events> <md-device>
+#/ 
+#/ Checks the raid-device status
+#/ 
+#/ Options:
+#/  -w, --warning=<events>      The events of when to trigger a warning (comma-separated)
+#/  -c, --critical=<events>     The events of when to trigger a critical warning (comma-separated)
+#/ 
+#/ Possible events
+#/ - clean
+#/ - write-pending
+#/ - active
+#/ - degraded
+#/ 
+#/ Exit Codes:
+#/  0 Everything OK
+#/  1 Warning events happened
+#/  2 Critical events happened
+#/  3 Unknown status
+#/
+
+
+Usage() {
+    grep '^#/' "${script_dir}/${script_name}" | sed 's/^#\/\w*//'
+}
+
+GetOptions() {
+    # https://stackoverflow.com/a/29754866
+    OPTIONS=w:c:
+    LONGOPTS=warning:,critical:
+
+    # -use ! and PIPESTATUS to get exit code with errexit set
+    # -temporarily store output to be able to check for errors
+    # -activate quoting/enhanced mode (e.g. by writing out “--options”)
+    # -pass arguments only via   -- "$@"   to separate them correctly
+    ! PARSED=$(getopt --options=$OPTIONS --longoptions=$LONGOPTS --name "$0" -- "$@")
+    if [[ ${PIPESTATUS[0]} -ne 0 ]]; then
+        # e.g. return value is 1
+        #  then getopt has complained about wrong arguments to stdout
+        Usage
+        exit 2
+    fi
+
+    # read getopt's output this way to handle the quoting right:
+    eval set -- "$PARSED"
+    OLDIFS=$IFS
+
+    # now enjoy the options in order and nicely split until we see --
+    while true; do
+        case "$1" in
+            -w|--warning)
+                IFS=","
+                warn=$(echo $2)
+                IFS=$OLDIFS
+                shift 2
+                ;;
+            -c|--critical)
+                IFS=","
+                crit=$(echo $2)
+                IFS=$OLDIFS
+                shift 2
+                ;;
+            --)
+                shift
+                break
+                ;;
+            *)
+                echo "MD UNKNOWN - ${1} is not a valid parameter"
+                exit 3
+                ;;
+        esac
+    done
+    if [ -z ${1+x} ]; then 
+        echo "MD UNKNOWN - MD-device not given"
+        exit 3
+    elif [ ! -d /sys/block/${1} ]; then 
+        echo "MD UNKNOWN - MD-device is not valid"
+        exit 3
+    else 
+        device=${1}
+    fi
+}
+LC_NUMERIC="C"
+warn='active'
+crit='degraded'
+device=''
+script_name=$(basename "${0}")
+script_dir=$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )
+GetOptions "$@"
+events=()
+
+degradeddevs=$(cat /sys/block/${device}/md/degraded)
+msg=()
+if [[ $degradeddevs > 0 ]]; then
+    actevents+=('degraded')
+    msg+=("$degradeddevs devices degraded")
+fi
+state=$(cat /sys/block/${device}/md/array_state)
+msg+=("Array ${device} is ${state}")
+actevents+=($state)
+
+rval=0
+rmsg="OK"
+for warnevent in $warn; do
+    if [[ " ${actevents[*]} " =~ " ${warnevent} " ]]; then
+        rval=1
+        rmsg="WARNING"
+    fi
+done
+
+for critevent in $crit; do
+    if [[ " ${actevents[*]} " =~ " ${critevent} " ]]; then
+        rval=2
+        rmsg="CRITICAL"
+    fi
+done
+
+msgprint=$( (IFS=$'\n'; echo "${msg[*]}") )
+echo "MD ${rmsg} - ${msgprint}"