versoon 1.3.29

TA-nmon/bin/nmon_external_cmd/nmon_external_snap.sh

@@ -37,14 +37,21 @@ echo "PROCCOUNT,$1,`ps -ef | wc -l`" >>NMON_FIFO_PATH/nmon_external.dat &
 echo "UPTIME,$1,\"`uptime | sed 's/^\s//g' | sed 's/,/;/g'`\"" >>NMON_FIFO_PATH/nmon_external.dat &
 
 # df table information
-DF_TABLE=`df -k -P | sed '1d' | egrep -v '\s\/proc$|\s/dev$|\s\/run$|^tmpfs.*\/dev.*$|^tmpfs.*\/run.*$|^tmpfs.*\/sys.*$|^tmpfs.*\/var.*$' | awk '{print $6}'`
+DF_TABLE=`df -k -P | sed '1d' | egrep -v '\/proc$|/dev$|\/run$|^tmpfs.*\/dev.*$|^tmpfs.*\/run.*$|^tmpfs.*\/sys.*$|^tmpfs.*\/var.*$' | awk '{print $6}'`
 for fs in $DF_TABLE; do
     echo "DF_STORAGE,$1,`df -k -P $fs | sed '1d' | sed 's/%//g' | sed 's/,/;/g' | awk '{print $1 "," $2 "," $3 "," $4 "," $5 "," $6}'`" >>NMON_FIFO_PATH/nmon_external.dat
-    # DF_INODES, for AIX and Linux
-    case `uname` in
-    "AIX")
-        echo "DF_INODES,$1,`df -i $fs | sed '1d' | sed 's/%//g' | sed 's/,/;/g' | awk '{print $1 "," $5 "," $6 "," $7}'`" >>NMON_FIFO_PATH/nmon_external.dat ;;
-    "Linux")
-        echo "DF_INODES,$1,`df -i -P $fs | sed '1d' | sed 's/%//g' | sed 's/,/;/g' | awk '{print $1 "," $2 "," $3 "," $4 "," $5 "," $6}'`" >>NMON_FIFO_PATH/nmon_external.dat ;;
-    esac
 done
+
+# DF_INODES, for AIX and Linux
+case `uname` in
+"AIX")
+    for fs in $DF_TABLE; do
+        echo "DF_INODES,$1,`df -i $fs | sed '1d' | sed 's/%//g' | sed 's/,/;/g' | awk '{print $1 "," $5 "," $6 "," $7}'`" >>NMON_FIFO_PATH/nmon_external.dat
+    done
+    ;;
+"Linux")
+    for fs in $DF_TABLE; do
+        echo "DF_INODES,$1,`df -i -P $fs | sed '1d' | sed 's/%//g' | sed 's/,/;/g' | awk '{print $1 "," $2 "," $3 "," $4 "," $5 "," $6}'`" >>NMON_FIFO_PATH/nmon_external.dat
+    done
+    ;;
+esac

TA-nmon/bin/nmon_helper.sh

@@ -1088,7 +1088,7 @@ check_duplicated_external_snap () {
 
         # get the list of occurrences
         count="0"
-        count=`ps -ef | grep splunk | grep nmon | grep nmon_external_snap | grep -v grep | wc -l`
+        count=`ps -ef | grep nmon_external_snap | grep -v grep | wc -l`
 
         if [ $count -gt 0 ]; then
                 oldPidList=`ps -ef | grep nmon_external_snap | grep -v grep | awk '{print $2}'`
@@ -1098,22 +1098,34 @@ check_duplicated_external_snap () {
                     if [ -d /proc/${pid} ]; then
                         # get the process runtime in seconds
                         pid_runtime=`ps -p ${pid} -oetime= | tr '-' ':' | awk -F: '{ total=0; m=1; } { for (i=0; i < NF; i++) {total += $(NF-i)*m; m *= i >= 2 ? 24 : 60 }} {print total}'`
-                        if [ ${pid_runtime} -gt 120 ]; then
-                            echo "`log_date`, ${HOST} WARN: fifo nmon external snap script took long and will be killed (SIGTERM): `ps -p ${pid} -ouser,pid,command,etime,args | grep -v PID`"
-                            kill $pid
 
-                            # Allow some time for the process to end
-                            sleep 1
+                        case ${pid_runtime} in
 
-                            # re-check the status
-                            ps -p ${pid} -oetime= >/dev/null
+                            ''|*[!0-9]*)
+                                echo "`log_date`, ${HOST} WARN: run time identification of processwith pid ${pid} failed, it has been probably terminated"
+                                ;;
+                            *)
 
-                            if [ $? -eq 0 ]; then
-                            echo "`log_date`, ${HOST} WARN, fifo nmon external snap due to `ps -eo user,pid,command,etime,args | grep $pid | grep -v grep` failed to stop, killing (-9) process $pid"
-                                kill -9 $pid
-                            fi
+                                if [ ${pid_runtime} -gt 120 ]; then
+                                    echo "`log_date`, ${HOST} WARN: fifo nmon external snap script took long and will be killed (SIGTERM): `ps -p ${pid} -ouser,pid,command,etime,args | grep -v PID`"
+                                    kill $pid
+
+                                    # Allow some time for the process to end
+                                    sleep 1
+
+                                    # re-check the status
+                                    ps -p ${pid} -oetime= >/dev/null
+
+                                    if [ $? -eq 0 ]; then
+                                    echo "`log_date`, ${HOST} WARN, fifo nmon external snap due to `ps -eo user,pid,command,etime,args | grep $pid | grep -v grep` failed to stop, killing (-9) process $pid"
+                                        kill -9 $pid
+                                    fi
+
+                                fi
+                                ;;
+
+                        esac
 
-                        fi
                     fi
                 done
         fi

docs/releasenotes.rst

@@ -20,6 +20,7 @@ V1.3.29:
 
 - fix: Python parser - header detection correction for nmon external monitoring
 - feature: Add df information for improved file system monitoring and storage capacity planning
+- fix: unexpected operator issue during process identification #48
 
 ========
 V1.3.28: