######################################################################
# customize per survey
-# specify either the obdecho client names or the obdfilter names
-client_names=()
-ost_names=(ost{1,2,3,4,5,6,7,8})
-
-# result file prefix
-rslt=/tmp/obdfilter_survey
-
-# lustre root (leave blank unless running with own source)
-lustre_root=
-
-# what to do (we always do an initial write)
-#tests="rewrite read reread rewrite_again"
-tests="rewrite read"
-
-# total size (MBytes)
-# large enough to avoid cache effects
-size=8192
-
-# record size (KBytes)
-rszlo=1024
-rszhi=1024
+# specify obd instances to exercise
+# these can be either...
+# obdfilter instances (set 'ost_names')
+# ...or...
+# echo_client instances (set 'client_names')
+# ... use 'host:name' for obd instances on other nodes.
+# allow these to be passed in via string...
+# OR
+# one can specify only case=disk or case=network or case=netdisk through
+# command line.
+
+# Perquisite: For "disk" case and "netdisk" case you need to have lustre setup
+# with one or more ost's. For "network" case you need to have all
+# modules (those llmount.sh loades) loaded in kernel. And the
+# 'lctl dl' output must be blank.
+
+# How to run test:
+# case 1 (local disk):
+# $ nobjhi=2 thrhi=2 size=1024 case=disk sh obdfilter-survey
+# one can also run test with user defined targets as follows,
+# $ nobjhi=2 thrhi=2 size=1024 targets="lustre-OST0000 lustre-OST0001 ..." sh obdfilter-survey
+# case 2 (network):
+# $ nobjhi=2 thrhi=2 size=1024 targets="<name/ip_of_server>" case=network sh obdfilter-survey
+# where, targets is name or ip address of system, which you want to
+# set as server.
+# case 3 (network and disk):
+# $ nobjhi=2 thrhi=2 size=1024 case=netdisk sh obdfilter-survey
+# one can also run test with user defined targets as follows,
+# $ nobjhi=2 thrhi=2 size=1024 targets="<osc_name> ..." sh obdfilter-survey
+#[ NOTE: It is advised to have automated login (passwordless entry) between server and
+# client systems on which this test runs.]
+
+# include library
+source libecho
+
+# The following variables can be set in the environment, or on the
+# command line
+# result file prefix (date/time + hostname makes unique)
+# NB ensure path to it exists
+rslt_loc=${rslt_loc:-"/tmp"}
+rslt=${rslt:-"$rslt_loc/obdfilter_survey_`date +%F@%R`_`uname -n`"}
+
+# Set this true to check file contents
+verify=${verify:-0}
+
+# total size (MBytes) per obd instance
+# large enough to avoid cache effects
+# and to make test startup/shutdown overhead insignificant
+size=${size:-16384}
+
+# record size (KBytes) ( 7168 max)
+rszlo=${rszlo:-1024}
+rszhi=${rszhi:-1024}
# number of objects per OST
-nobjlo=1
-nobjhi=32
+nobjlo=${nobjlo:-1}
+#was nobjhi=${nobjhi:-512}
+nobjhi=${nobjhi:-16}
# threads per OST (1024 max)
-thrlo=1
-thrhi=128
-
-# restart from here iff all are defined
-restart_rsz=
-restart_thr=1
-restart_nobj=1
-
-# machine's page size
-PAGE_SIZE=64
-
-# max buffer_mem (total_threads * buffer size)
-# (to avoid lctl ENOMEM problems)
-max_buffer_mem=$((256*1024))
-
-#####################################################################
-
-snap=1
-verify=1
-
-check_obdecho() {
- lsmod | grep obdecho > /dev/null 2>&1
-}
-
-check_obdecho
-load_obdecho=$(($? != 0))
-
-if [ -z "$lustre_root" ]; then
- lctl=lctl
- if ((load_obdecho)); then
- modprobe obdecho
- fi
-else
- lctl=${lustre_root}/lctl
- if ((load_obdecho)); then
- if [ -f ${lustre_root}/obdecho/obdecho.ko ]; then
- insmod ${lustre_root}/obdecho/obdecho.ko
- else
- insmod ${lustre_root}/obdecho/obdecho.o
- fi
- fi
-fi
+thrlo=${thrlo:-1}
+thrhi=${thrhi:-16}
-check_obdecho || (echo "Can't load obdecho"; exit 1)
-
-get_devno () {
- local type=$1
- local name=$2
- $lctl device_list | awk "{if (\$2 == \"UP\" && \$3 == \"$type\" && \$4 == \"$name\") {\
- print \$1; exit}}"
-}
-
-get_ec_devno () {
- local idx=$1
- local client_name=${client_names[idx]}
- local ost_name=${ost_names[idx]}
- if [ -z "$client_name" ]; then
- if [ -z "$ost_name" ]; then
- echo "client and ost name both null" 1>&2
- return
- fi
- client_name=${ost_name}_echo_client
- fi
- ec=`get_devno echo_client $client_name`
- if [ -n "$ec" ]; then
- echo $ec $client_name
- return
- fi
- if [ -z "$ost_name" ]; then
- echo "no echo client and ost_name not set" 1>&2
- return
- fi
- ost=`get_devno obdfilter $ost_name`
- if [ -z "$ost" ]; then
- echo "OST $ost_name not setup" 1>&2
- return
- fi
- $lctl <<EOF
- attach echo_client $client_name ${client_name}_UUID
- setup $ost_name
-EOF
- ec=`get_devno echo_client $client_name`
- if [ -z "$ec" ]; then
- echo "Can't setup echo client" 1>&2
- return
- fi
- echo $ec $client_name 1
-}
-
-teardown_ec_devno () {
- local idx=$1
- local client_name=${client_names[$idx]}
- if ((do_teardown_ec[$idx])); then
- $lctl <<EOF
- cfg $client_name
- cleanup
- detach
-EOF
- fi
-}
+# End of variables
+# create a set of objects, check there are 'n' contiguous ones and
+# return the first or 'ERROR'
+# parameter: 1. hostname
+# 2. device number
+# 3. number of object to be created (specified by user)
+# 4. tempfile name
create_objects () {
- # create a set of objects, check there are 'n' contiguous ones and
- # return the first or 'ERROR'
- local devno=$1
- local nobj=$2
- local rfile=$3
- $lctl --device $devno create $nobj > $rfile 2>&1
- n=(`awk < $rfile \
- '/is object id/ {obj=strtonum($6);\
- first=!not_first; not_first=1;\
- if (first) first_obj=obj;
- else if (obj != prev + 1) exit;\
- prev=obj; n++}\
- END {printf "%d %d\n", first_obj, n}'`)
- if ((n[1] != nobj)); then
- echo "ERROR"
- else
- echo ${n[0]}
+ local host=$1
+ local devno=$2
+ local nobj=$3
+ local rfile=$4
+ remote_shell $host $lctl --device $devno create $nobj > $rfile 2>&1
+ first=0
+ prev=0
+ count=0
+ error=0
+ while read line; do
+ echo "$line" | grep -q 'is object id'
+ if [ $? -ne 0 ]; then
+ continue
+ fi
+ if [ $first -eq 0 ]; then
+ first=$(echo $line | awk '{print $6}')
+ first=$(printf "%d" $first)
+ prev=$first
+ count=1
+ else
+ obj=$(echo $line | awk '{print $6}')
+ obj=$(printf "%d" $obj)
+ diff=$((obj - (prev+1)))
+ if [ $diff -ne 0 ]; then
+ error=1
+ fi
+ prev=$obj
+ count=$((count+1))
+ fi
+ done < $rfile
+ if [ $nobj -ne $count ]; then
+ echo "ERROR: $nobj != $count" >&2
+ cat $rfile >&2
+ echo "ERROR"
+ elif [ $error -ne 0 ]; then
+ echo "ERROR: non contiguous objs found" >&2
+ else
+ echo $first
fi
}
+# destroys all objects created in create_objects routine
+# parameter: 3. start obj id.
destroy_objects () {
- local devno=$1
- local obj0=$2
- local nobj=$3
- local rfile=$4
- $lctl --device $devno destroy $obj0 $nobj > $rfile 2>&1
+ local host=$1
+ local devno=$2
+ local obj0=$3
+ local nobj=$4
+ local rfile=$5
+ remote_shell $host $lctl --device $devno destroy $obj0 $nobj > $rfile 2>&1
}
get_stats () {
local rfile=$1
- awk < $rfile \
+ gawk < $rfile \
'/^Selected device [0-9]+$/ {n = 0; next}\
/error/ {n = -1; exit}\
/^[0-9]+\/[0-9]+ Total: [0-9]+\.[0-9]+\/second$/ {n++; v=strtonum($3); \
printf "%d %f %f\n", err, min, max}'
}
+# enable or disable data check.
+# parameter: 1. read/write
testname2type () {
# 'x' disables data check
if ((verify)); then
esac
}
-start=`date +%F@%R`
-rsltf="${rslt}_${start}.summary"
-echo -n > $rsltf
-workf="${rslt}_${start}.detail"
-echo -n > $workf
-
print_summary () {
if [ "$1" = "-n" ]; then
- minusn=$1; shift
+ minusn=$1; shift
else
- minusn=""
+ minusn=""
fi
echo $minusn "$*" >> $rsltf
echo $minusn "$*"
}
-ndevs=${#client_names[@]}
-if ((ndevs < ${#ost_names[@]} )); then
- ndevs=${#ost_names[@]}
+# Customisation variables
+#####################################################################
+# One can change variable values in this section as per requirements
+
+targets=${targets:-""}
+case=${case:-"disk"}
+if [ -n "$targets" ]; then
+ declare -a ost_names
+ declare -a client_names
+ count=0
+ for name in $targets; do
+ if [ $case == "disk" ]; then
+ ost_names[$count]=$name
+ else
+ client_names[$count]=$name
+ fi
+ count=$((count+1))
+ done
fi
-for ((idx = 0; idx < ndevs; idx++)); do
- devno=(`get_ec_devno $idx`)
- if ((${#devno[@]} < 2)); then
- exit 1
+# what tests to run (first must be write)
+tests_str=${tests_str:-""}
+if [ -n "$tests_str" ]; then
+ declare -a tests
+ count=0
+ for name in $tests_str; do
+ tests[$count]=$name
+ count=$((count+1))
+ done
+else
+ #tests=(write rewrite read reread rewrite_again)
+ #tests=(write rewrite read)
+ tests=(write)
+fi
+
+# restart from here iff all are defined
+restart_rsz=
+restart_thr=1
+restart_nobj=1
+
+# machine's page size (K)
+if [ -z "$PAGE_SIZE" ]; then
+ if which python >/dev/null; then
+ PAGE_SIZE=`echo 'import resource; print resource.getpagesize()/1024;' |python`
fi
- devnos[$idx]=${devno[0]}
- client_names[$idx]=${devno[1]}
- do_teardown_ec[$idx]=$((${#devno[@]} > 2))
-done
+fi
+PAGE_SIZE=${PAGE_SIZE:-4}
-echo 0 > /proc/sys/portals/debug
+# max buffer_mem (total_threads * buffer size)
+# (to avoid lctl ENOMEM problems)
+max_buffer_mem=$((1024 * 1024))
+snap=1
+clean_srv_OSS=0
+# Customisation variables ends here.
+#####################################################################
+# leave the rest of this alone unless you know what you're doing...
+
+# check and insert obdecho module
+if ! lsmod | grep obdecho > /dev/null; then
+ modprobe obdecho
+fi
+if [ ${#tests[@]} -eq 0 -o "${tests[0]}" != "write" ]; then
+ echo "tests: ${tests[@]}"
+ echo "First test must be 'write'" 1>&2
+ exit 1
+fi
+
+rsltf="${rslt}.summary"
+workf="${rslt}.detail"
+cmdsf="${rslt}.script"
+vmstatf="${rslt}.vmstat"
+echo -n > $rsltf
+echo -n > $workf
+
+# hide a little trick to unset this from the command line
+if [ "$lustre_root" == " " ]; then
+ unset lustre_root
+fi
-for ((rsz=$rszlo;rsz<=$rszhi;rsz*=2)); do
- for ((nobj=$nobjlo;nobj<=$nobjhi;nobj*=2)); do
- for ((thr=$thrlo;thr<=$thrhi;thr*=2)); do
- if ((thr < nobj)); then
+if [ -z "$lustre_root" ]; then
+ lctl=lctl
+else
+ lctl=${lustre_root}/utils/lctl
+fi
+
+# split out hostnames from client/ost names
+ndevs=0
+for trgt in $targets; do
+ str=(`split_hostname $trgt`)
+ host_names[$ndevs]=${str[0]}
+ client_names[$ndevs]=${str[1]}
+ ndevs=$((ndevs+1))
+done
+if [ $case == "netdisk" ]; then
+ if [ "$targets" ]; then
+ for ((i = 0; i < $ndevs; i++)); do
+ setup_osc_for_remote_ost ${host_names[$i]} ${client_names[$i]} $i
+ cleanup_oscs="$cleanup_oscs ${client_names[$i]}_osc"
+ host_names[$i]=localhost
+ done
+ fi
+ declare -a osc_names
+ declare -a osc_uuids
+ osc_names_str=$(lctl dl |grep osc | awk "{if (\$2 == \"UP\" && \$3 == \"osc\") {print \$4} }")
+ count=0;
+ for name in $osc_names_str; do
+ osc_names[$count]=$name
+ count=$((count+1))
+ done
+ osc_uuid_str=$(lctl dl |grep osc | awk "{if (\$2 == \"UP\" && \$3 == \"osc\") {print \$5} }")
+ count=0;
+ for uuid in $osc_uuid_str; do
+ osc_uuids[$count]=$uuid
+ count=$((count+1))
+ done
+ for (( i = 0; i < $count; i++ ))
+ do
+ ec_using_osc ${osc_names[$i]}
+ done
+ echo_clients=$(lctl dl | grep echo_client | awk "{if (\$2 == \"UP\" && \$3 == \"echo_client\") {print \$4} }")
+ cnt=0;
+ for name in $echo_clients; do
+ client_names[$cnt]=$name
+ host_names[$cnt]=localhost
+ cnt=$((cnt+1))
+ done
+ ndevs=${#client_names[@]}
+fi
+if [ $case == "network" ]; then
+ server_nid=$targets
+ if [ -z "$server_nid" ]; then
+ echo "Specify hostname or ip-address of server"
+ exit 1;
+ fi
+ # check for obdecho module on server
+ if ! dsh $server_nid root "lsmod | grep obdecho > /dev/null"; then
+ dsh $server_nid root "modprobe obdecho"
+ fi
+ # Now do the server setup
+ setup_srv_obd $server_nid "echo_srv"
+ oss_on_srv=`dsh $server_nid root "lctl dl | grep OSS" | awk '{ print $4 }'`
+ if [ -z $oss_on_srv ]; then
+ setup_OSS $server_nid
+ clean_srv_OSS=1
+ fi
+ if ! dsh $server_nid root "lctl dl | grep obdecho > /dev/null 2>&1"; then
+ echo "obdecho not setup on server"
+ exit 1
+ fi
+ if ! dsh $server_nid root "lctl dl | grep ost > /dev/null 2>&1"; then
+ echo "ost not setup on server"
+ exit 1
+ fi
+ # Now start client setup
+ osc_names_str=$(lctl dl)
+ if [ -n "$osc_names_str" ]; then
+ echo "The existing setup must be cleaned";
+ exit 0;
+ fi
+ ec_using_srv_nid $server_nid "echotmp" "echotmp_UUID"
+ client_names[0]="echotmp_ecc"
+fi
+if [ -z "$targets" ]; then
+ if [ $case == "disk" ]; then
+ get_targets
+ ndevs=${#ost_names[@]}
+ fi
+fi
+# get vmstat started
+# disable portals debug and get obdecho loaded on all relevant hosts
+unique_hosts=(`unique ${host_names[@]}`)
+pidcount=0
+for host in ${unique_hosts[@]}; do
+ host_vmstatf=${vmstatf}_${host}
+ echo -n > $host_vmstatf
+ remote_shell $host "vmstat 5 >> $host_vmstatf" &
+ pid=$!
+ vmstatpids[$pidcount]=$pid
+ pidcount=$((pidcount+1))
+ do_unload_obdecho[$host]=0
+ if obdecho_loaded $host; then
+ continue
+ fi
+ load_obdecho $host
+ if obdecho_loaded $host; then
+ do_unload_obdecho[$host]=1
+ continue
+ fi
+ echo "Can't load obdecho on $host" 1>&2
+ exit 1
+done
+# get all the echo_client device numbers and names
+for ((i=0; i < $ndevs; i++)); do
+ host=${host_names[$i]}
+ devno=(`get_ec_devno $host "${client_names[$i]}" "${ost_names[$i]}"`)
+ if ((${#devno[@]} != 3)); then
+ exit 1
+ fi
+ devnos[$i]=${devno[0]}
+ client_names[$i]=${devno[1]}
+ do_teardown_ec[$i]=${devno[2]}
+done
+if (($ndevs <= 0 || ${#host_names[@]} <= 0)); then
+ echo "no devices or hosts specified"
+ cleanup 0 $clean_srv_OSS $cleanup_oscs
+fi
+print_summary "$(date) Obdfilter-survey for case=$case from $(hostname)"
+for ((rsz = $rszlo; rsz <= $rszhi; rsz*=2)); do
+ for ((nobj = $nobjlo; nobj <= $nobjhi; nobj*=2)); do
+ for ((thr = $thrlo; thr <= $thrhi; thr*=2)); do
+ if ((thr % nobj)); then
continue
fi
# restart?
fi
# create the objects
tmpf="${workf}_tmp"
- for ((idx=0; idx < ndevs; idx++)); do
+ for ((idx = 0; idx < $ndevs; idx++)); do
+ host=${host_names[$idx]}
devno=${devnos[$idx]}
- first_obj=`create_objects $devno $nobj $tmpf`
- echo "========> Create [$idx]" >> $workf
+ client_name="${host}:${client_names[$idx]}"
+ echo "=============> Create $nobj on $client_name" >> $workf
+ first_obj=`create_objects $host $devno $nobj $tmpf`
cat $tmpf >> $workf
rm $tmpf
if [ $first_obj = "ERROR" ]; then
- print_summary "created object #s [$idx] not contiguous"
+ print_summary "created object #s on $client_name not contiguous"
exit 1
fi
first_objs[$idx]=$first_obj
done
- for test in write $tests; do
+ # run tests
+ for test in ${tests[@]}; do
+ declare -a pidarray
+ for host in ${unique_hosts[@]}; do
+ echo "starting run for test: $test rsz: $rsz threads: $thr objects: $nobj" >> ${vmstatf}_${host}
+ done
print_summary -n "$test "
- t0=`date +%s.%N`
- for ((idx=0; idx < ndevs; idx++)); do
+ # create per-host script files
+ for host in ${unique_hosts[@]}; do
+ echo -n > ${cmdsf}_${host}
+ done
+ for ((idx = 0; idx < $ndevs; idx++)); do
+ host=${host_names[$idx]}
devno=${devnos[$idx]}
tmpfi="${tmpf}_$idx"
first_obj=${first_objs[$idx]}
- $lctl > $tmpfi 2>&1 \
- --threads $thr -$snap $devno \
- test_brw $count `testname2type $test` q $pages ${thr}t${first_obj} &
- done
- wait
- t1=`date +%s.%N`
+ thr_per_obj=$((${thr}/${nobj}))
+ echo >> ${cmdsf}_${host} \
+ "$lctl > $tmpfi 2>&1 \\
+ --threads $thr -$snap $devno \\
+ test_brw $count `testname2type $test` q $pages ${thr_per_obj}t${first_obj} &"
+ done
+ pidcount=0
+ for host in ${unique_hosts[@]}; do
+ echo "wait" >> ${cmdsf}_${host}
+ pidarray[$pidcount]=0
+ pidcount=$((pidcount+1))
+ done
+ # timed run of all the per-host script files
+ t0=`date +%s.%N`
+ pidcount=0
+ for host in ${unique_hosts[@]}; do
+ remote_shell $host bash < ${cmdsf}_${host} &
+ pidarray[$pidcount]=$!
+ pidcount=$((pidcount+1))
+ done
+ pidcount=0
+ for host in ${unique_hosts[@]}; do
+ wait ${pidarray[$pidcount]}
+ pidcount=$((pidcount+1))
+ done
+ #wait
+ t1=`date +%s.%N`
+ # clean up per-host script files
+ for host in ${unique_hosts[@]}; do
+ rm ${cmdsf}_${host}
+ done
+ # compute bandwidth from total data / elapsed time
str=`awk "BEGIN {printf \"%7.2f \",\
$total_size / (( $t1 - $t0 ) * 1024)}"`
print_summary -n "$str"
+ # collect/check individual OST stats
echo -n > $tmpf
- for ((idx=0; idx < ndevs; idx++)); do
+ for ((idx = 0; idx < $ndevs; idx++)); do
+ client_name="${host_names[$idx]}:${client_names[$idx]}"
tmpfi="${tmpf}_$idx"
- echo "========> $test [$idx]" >> $workf
- cat $tmpfi >> $workf
+ echo "=============> $test $client_name" >> $workf
+ host="${host_names[$idx]}"
+ remote_shell $host cat $tmpfi >> $workf
get_stats $tmpfi >> $tmpf
rm $tmpfi
done
- echo "========> $test [$idx] global" >> $workf
+ # compute/display global min/max stats
+ echo "=============> $test global" >> $workf
cat $tmpf >> $workf
stats=(`get_global_stats $tmpf`)
rm $tmpf
if ((stats[0] <= 0)); then
if ((stats[0] < 0)); then
- str=`printf "%15s " ERROR`
+ str=`printf "%17s " ERROR`
else
- str=`printf "%15s " SHORT`
+ str=`printf "%17s " SHORT`
fi
else
- str=`awk "BEGIN {printf \"[%6.2f,%6.2f] \",\
+ str=`awk "BEGIN {printf \"[%7.2f,%7.2f] \",\
(${stats[1]} * $actual_rsz)/1024,\
(${stats[2]} * $actual_rsz)/1024; exit}"`
fi
print_summary -n "$str"
done
print_summary ""
- for ((idx=0; idx < ndevs; idx++)); do
+ # destroy objects we created
+ for ((idx = 0; idx < $ndevs; idx++)); do
+ host=${host_names[$idx]}
devno=${devnos[$idx]}
+ client_name="${host}:${client_names[$idx]}"
first_obj=${first_objs[$idx]}
- destroy_objects $devno $first_obj $nobj $tmpf
- echo "========> Destroy [$idx]" >> $workf
+ echo "=============> Destroy $nobj on $client_name" >> $workf
+ destroy_objects $host $devno $first_obj $nobj $tmpf
cat $tmpf >> $workf
rm $tmpf
done
done
done
done
-
-for ((idx=0; idx < ndevs; idx++)); do
- teardown_ec_devno $idx
-done
-
-if ((load_obdecho)); then
- rmmod obdecho
-fi
+cleanup 0 $clean_srv_OSS $cleanup_oscs
+exit 0
git://git.whamcloud.com / fs / lustre-release.git / blobdiff