#!/bin/bash # Need bc # Some parts are rudimental.. # sudo vim ./share/perl5/Munin/Master/GraphOld.pm # http://munin-monitoring.org/ticket/1352 # http://munin-monitoring.org/ticket/1017 ###################################################################################################################### # Plugin to monitor basic statistics of EMC VNX 5300 Unified Datamovers # ###################################################################################################################### # Author: Evgeny Beysembaev ##################################### # Description # ##################################### # The plugin monitors basic statistics of EMC Unified Storage system Datamovers. Probably it can also be compatible with # other Isilon or Celerra systems. It uses SSH to connect to Control Stations, then remotely executes # /nas/sbin/server_stats and fetches and parses data from it. It supports gathering data both from active/active # and active/passive Datamover configurations, ignoring offline or standby Datamovers. If all Datamovers are # offline or absent, the plugin returns error. # This plugin also automatically chooses Primary Control Station from the list by calling /nasmcd/sbin/getreason and # /nasmcd/sbin/t2slot. # # Data is gathered from basic-std Statistics Group # # It's quite easy to comment out unneeded data to make graphs less overloaded or to add new statistics sources. ##################################### # Configuration # ##################################### # The plugin uses SSH to connect to Control Stations. It's possible to use 'nasadmin' user, but it would be better # if you create read-only global user by Unisphere Client. The user should have only Operator role. # I created "operator" user but due to the fact that Control Stations already had one internal "operator" user, # the new one was called "operator1". So be careful. # # On munin-node side choose a user which will be used to connect through SSH. Generally user "munin" is ok. Then, # execute "sudo su munin -s /bin/bash", "ssh-keygen" and "ssh-copy-id" to both Control Stations with newly created # user. # # Make a link from /usr/share/munin/plugins/emc_vnx_dm_basic_stats to /etc/munin/plugins/emc_vnx_dm_basic_stats_, # where is any arbitrary name of your storage system. The plugin will return in its answer # as "host_name" field. # Assume your storage system is called "VNX5300". # # Make a configuration file at /etc/munin/plugin-conf.d/emc_vnx_dm_basic_stats_VNX5300 # # [emc_vnx_dm_basic_stats_VNX5300] # user munin # SSH Client local user # env.username operator1 # Remote user with Operator role # env.cs_addr 192.168.1.1 192.168.1.2 # Control Stations addresses # env.nas_servers server_2 server_3 # This is the default value and can be omitted ##################################### # History # ##################################### # 09.11.2016 - First Release ###################################################################################################################### export LANG=C TARGET=$(echo "${0##*/}" | cut -d _ -f 6) #: ${nas_servers:="server_2 server_3"} SSH_CHECK='ssh -q $username@$CS "/nasmcd/sbin/getreason | grep -w slot_\`/nasmcd/sbin/t2slot\` | cut -d- -f1"' if [ "$1" = "autoconf" ]; then echo "yes" exit 0 fi if [ -z "$username" ]; then echo "No username!" exit 1 fi if [ -z "$cs_addr" ]; then echo "No control station addresses!" exit 1 fi #Choosing Cotrol Station. Code have to be "10" for CS in $cs_addr; do if [ "`eval $SSH_CHECK`" -eq "10" ]; then # echo "$CS is Primary" PRIMARY_CS=$CS break fi done if [ -z "$PRIMARY_CS" ]; then echo "No alive primary Control Station from list \"$cs_addr\""; exit 1; fi SP="SPA" #TODO SPALL="SPA SPB" #TODO SSH="ssh -q $username@$PRIMARY_CS " NAVICLI="/nas/sbin/navicli -h $SP" # Get Lun List LUNLIST="$($SSH $NAVICLI lun -list -drivetype | grep Name | sed -ne 's/^Name:\ *//p')" echo "host_name ${TARGET} " if [ "$1" = "config" ] ; then echo "multigraph emc_vnx_block_blocks graph_category disk graph_title EMC VNX 5300 LUN Blocks graph_vlabel Blocks Read (-) / Written (+) graph_args --base 1000" while read -r LUN ; do echo "${LUN}_read.label none ${LUN}_read.graph no ${LUN}_read.min 0 ${LUN}_read.draw AREA ${LUN}_read.type DERIVE ${LUN}_write.label $LUN Blocks ${LUN}_write.negative ${LUN}_read ${LUN}_write.type DERIVE ${LUN}_write.min 0 ${LUN}_write.draw STACK" done <<< $LUNLIST echo -e "\nmultigraph emc_vnx_block_req graph_category disk graph_title EMC VNX 5300 LUN Requests graph_vlabel Requests: Read (-) / Write (+) graph_args --base 1000" while read -r LUN ; do echo "${LUN}_readreq.label none ${LUN}_readreq.graph no ${LUN}_readreq.min 0 ${LUN}_readreq.type DERIVE ${LUN}_writereq.label $LUN Requests ${LUN}_writereq.negative ${LUN}_readreq ${LUN}_writereq.type DERIVE ${LUN}_writereq.min 0" done <<< $LUNLIST echo -e "\nmultigraph emc_vnx_block_ticks graph_category disk graph_title EMC VNX 5300 Counted Load per LUN graph_vlabel Load, % * Number of LUNs graph_args --base 1000 -l 0 -r " echo -n "graph_order " while read -r LUN ; do echo -n "${LUN}_busyticks ${LUN}_idleticks ${LUN}_bta=${LUN}_busyticks_spa ${LUN}_idleticks_spa ${LUN}_btb=${LUN}_busyticks_spb ${LUN}_idleticks_spb " done <<< $LUNLIST echo "" while read -r LUN ; do echo "${LUN}_busyticks_spa.label $LUN Busy Ticks SPA ${LUN}_busyticks_spa.type DERIVE ${LUN}_busyticks_spa.draw AREA ${LUN}_busyticks_spa.graph no ${LUN}_bta.label $LUN Busy Ticks SPA ${LUN}_bta.graph 0 ${LUN}_idleticks_spa.label $LUN Idle Ticks SPA ${LUN}_idleticks_spa.type DERIVE ${LUN}_idleticks_spa.draw AREA ${LUN}_idleticks_spa.graph no ${LUN}_busyticks_spb.label $LUN Busy Ticks SPB ${LUN}_busyticks_spb.type DERIVE ${LUN}_busyticks_spb.draw AREA ${LUN}_busyticks_spb.graph no ${LUN}_btb.label $LUN Busy Ticks SPB ${LUN}_btb.graph 0 ${LUN}_idleticks_spb.label $LUN Idle Ticks SPB ${LUN}_idleticks_spb.type DERIVE ${LUN}_idleticks_spb.draw AREA ${LUN}_idleticks_spb.graph no" echo "${LUN}_load_spa.label $LUN load SPA ${LUN}_load_spa.draw AREASTACK ${LUN}_load_spb.label $LUN load SPB ${LUN}_load_spb.draw AREASTACK ${LUN}_load_spa.cdef 100,${LUN}_bta,${LUN}_busyticks_spa,${LUN}_idleticks_spa,+,/,* ${LUN}_load_spb.cdef 100,${LUN}_btb,${LUN}_busyticks_spa,${LUN}_idleticks_spa,+,/,* " done <<< $LUNLIST echo -e "\nmultigraph emc_vnx_block_outstanding graph_category disk graph_title EMC VNX 5300 Sum of Outstanding Requests graph_vlabel Requests graph_args --base 1000" while read -r LUN ; do echo "${LUN}_outstandsum.label $LUN ${LUN}_outstandsum.type DERIVE" done <<< $LUNLIST echo -e "\nmultigraph emc_vnx_block_nonzeroreq graph_category disk graph_title EMC VNX 5300 Non-Zero Request Count Arrivals graph_vlabel Count Arrivals graph_args --base 1000" while read -r LUN ; do echo "${LUN}_nonzeroreq.label $LUN ${LUN}_nonzeroreq.type DERIVE" done <<< $LUNLIST echo -e "\nmultigraph emc_vnx_block_trespasses graph_category disk graph_title EMC VNX 5300 Trespasses graph_vlabel Trespasses" while read -r LUN ; do echo "${LUN}_implic_tr.label ${LUN} Implicit Trespasses ${LUN}_explic_tr.label ${LUN} Explicit Trespasses" done <<< $LUNLIST echo -e "\nmultigraph emc_vnx_block_queue graph_category disk graph_title EMC VNX 5300 Queue Length graph_vlabel Length" #echo -n "graph_order " #while read -r LUN ; do # echo -n "${LUN}_bta=${LUN}_btspa ${LUN}_btb=${LUN}_btspb " # done <<< $LUNLIST #echo "" while read -r LUN ; do echo "${LUN}_btspa.label ${LUN}" echo "${LUN}_btspa.graph no" echo "${LUN}_btspa.type DERIVE" # echo "${LUN}_bta.label ${LUN}" # echo "${LUN}_bta.graph no" # echo "${LUN}_bta.type DERIVE" echo "${LUN}_idspa.label ${LUN}" echo "${LUN}_idspa.graph no" echo "${LUN}_idspa.type DERIVE" echo "${LUN}_btspb.label ${LUN}" echo "${LUN}_btspb.graph no" echo "${LUN}_btspb.type DERIVE" # echo "${LUN}_btb.label ${LUN}" # echo "${LUN}_btb.graph no" # echo "${LUN}_btb.type DERIVE" echo "${LUN}_idspb.label ${LUN}" echo "${LUN}_idspb.graph no" echo "${LUN}_idspb.type DERIVE" echo "${LUN}_oss.label ${LUN}" echo "${LUN}_oss.graph no" echo "${LUN}_oss.type DERIVE" echo "${LUN}_nzr.label ${LUN}" echo "${LUN}_nzr.graph no" echo "${LUN}_nzr.type DERIVE" echo "${LUN}_rr.label ${LUN}" echo "${LUN}_rr.graph no" echo "${LUN}_rr.type DERIVE" echo "${LUN}_wr.label ${LUN}" echo "${LUN}_wr.graph no" echo "${LUN}_wr.type DERIVE" # echo "${LUN}_w_p_r.label ${LUN}" # echo "${LUN}_w_p_r.graph no" # echo "${LUN}_w_p_r.cdef ${LUN}_writereq,${LUN}_readreq,+" echo "${LUN}_ql_l_a.label ${LUN} Queue Length SPA" # echo "${LUN}_ql_l.cdef ${LUN}_bta,${LUN}_oss,${LUN}_nzr,2,${LUN}_wr,${LUN}_rr,+,/,-,/,*,${LUN}_btspa,${LUN}_idspa,+,/" echo "${LUN}_ql_l_a.cdef ${LUN}_oss,${LUN}_nzr,2,/,-,${LUN}_rr,${LUN}_wr,+,/,${LUN}_btspa,*,${LUN}_btspa,${LUN}_idspa,+,/" echo "${LUN}_ql_l_b.label ${LUN} Queue Length SPB" echo "${LUN}_ql_l_b.cdef ${LUN}_oss,${LUN}_nzr,2,/,-,${LUN}_rr,${LUN}_wr,+,/,${LUN}_btspb,*,${LUN}_btspb,${LUN}_idspb,+,/" # echo "${LUN}_ql_l.cdef ${LUN}_oss,${LUN}_nzr,2,/,-,${LUN}_rr,${LUN}_wr,+,/,5000,*" done <<< $LUNLIST exit 0 fi # -list -perfData BIGSSHCMD="$SSH" while read -r LUN ; do BIGSSHCMD+="$NAVICLI lun -list -name $LUN -perfData | sed -ne 's/^Blocks Read\:\ */${LUN}_read.value /p; s/^Blocks Written\:\ */${LUN}_write.value /p; s/Read Requests\:\ */${LUN}_readreq.value /p; s/Write Requests\:\ */${LUN}_writereq.value /p; s/Busy Ticks SP A\:\ */${LUN}_busyticks_spa.value /p; s/Idle Ticks SP A\:\ */${LUN}_idleticks_spa.value /p; s/Busy Ticks SP B\:\ */${LUN}_busyticks_spb.value /p; s/Idle Ticks SP B\:\ */${LUN}_idleticks_spb.value /p; s/Sum of Outstanding Requests\:\ */${LUN}_outstandsum.value /p; s/Non-Zero Request Count Arrivals\:\ */${LUN}_nonzeroreq.value /p; s/Implicit Trespasses\:\ */${LUN}_implic_tr.value /p; s/Explicit Trespasses\:\ */${LUN}_explic_tr.value /p; ' ;" done <<< $LUNLIST ANSWER="$($BIGSSHCMD)" echo "multigraph emc_vnx_block_blocks" echo "$ANSWER" | grep "read\.\|write\." echo -e "\nmultigraph emc_vnx_block_req" echo "$ANSWER" | grep "readreq\.\|writereq\." echo -e "\nmultigraph emc_vnx_block_ticks" while read -r LUN ; do LBTSPA=$(echo "$ANSWER" | sed -ne "s/^${LUN}_busyticks_spa\.value //p") LIDSPA=$(echo "$ANSWER" | sed -ne "s/^${LUN}_idleticks_spa\.value //p") LBTSPB=$(echo "$ANSWER" | sed -ne "s/^${LUN}_busyticks_spb\.value //p") LIDSPB=$(echo "$ANSWER" | sed -ne "s/^${LUN}_idleticks_spb\.value //p") # echo "${LUN}_load_spa.value" "$(( $LBTSPA*100 / ($LBTSPA+$LIDSPA) ))" # echo "${LUN}_load_spb.value" "$(( $LBTSPB*100 / ($LBTSPB+$LIDSPB) ))" echo "${LUN}_load_spa.value 0" echo "${LUN}_load_spb.value 0" done <<< $LUNLIST echo "$ANSWER" | grep "busyticks_spa\.\|idleticks_spa\." echo "$ANSWER" | grep "busyticks_spb\.\|idleticks_spb\." echo -e "\nmultigraph emc_vnx_block_outstanding" echo "$ANSWER" | grep "outstandsum\." echo -e "\nmultigraph emc_vnx_block_nonzeroreq" echo "$ANSWER" | grep "nonzeroreq\." echo -e "\nmultigraph emc_vnx_block_trespasses" echo "$ANSWER" | grep "implic_tr\.\|explic_tr\." echo -e "\nmultigraph emc_vnx_block_queue" # Queue Length while read -r LUN ; do # Queue Length SPA = ((Sum of Outstanding Requests SPA - NonZero Request Count Arrivals SPA / 2)/(Host Read Requests SPA + Host Write Requests SPA))* # (Busy Ticks SPA/(Busy Ticks SPA + Idle Ticks SPA) # We count together SPA and SPB, although it is not fully corrext SOR=$(echo "$ANSWER" | sed -ne "s/^${LUN}_outstandsum\.value //p") NZRCA=$(echo "$ANSWER" | sed -ne "s/^${LUN}_nonzeroreq\.value //p") RR=$(echo "$ANSWER" | sed -ne "s/^${LUN}_readreq\.value //p") WR=$(echo "$ANSWER" | sed -ne "s/^${LUN}_writereq\.value //p") echo "$ANSWER" | sed -ne "s/^${LUN}_busyticks_spa\./${LUN}_btspa\./p" echo "$ANSWER" | sed -ne "s/^${LUN}_idleticks_spa\./${LUN}_idspa\./p" echo "$ANSWER" | sed -ne "s/^${LUN}_busyticks_spb\./${LUN}_btspb\./p" echo "$ANSWER" | sed -ne "s/^${LUN}_idleticks_spb\./${LUN}_idspb\./p" echo "$ANSWER" | grep "${LUN}_busyticks_spa\.\|${LUN}_idleticks_spa\." echo "$ANSWER" | grep "${LUN}_busyticks_spb\.\|${LUN}_idleticks_spb\." echo "$ANSWER" | sed -ne "s/^${LUN}_outstandsum\./${LUN}_oss\./p" echo "$ANSWER" | sed -ne "s/^${LUN}_nonzeroreq\./${LUN}_nzr\./p" echo "${LUN}_writereq_plus_readreq.value 0" echo "$ANSWER" | sed -ne "s/^${LUN}_readreq\./${LUN}_rr\./p" echo "$ANSWER" | sed -ne "s/^${LUN}_writereq\./${LUN}_wr\./p" echo "${LUN}_ql_l_a.value 0 " echo "${LUN}_ql_l_b.value 0 " done <<< $LUNLIST exit 0