do_hbm_test.sh 12.1 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
#
# Copyright (c) 2019 Facebook
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of version 2 of the GNU General Public
# License as published by the Free Software Foundation.

Usage() {
  echo "Script for testing HBM (Host Bandwidth Manager) framework."
  echo "It creates a cgroup to use for testing and load a BPF program to limit"
  echo "egress or ingress bandwidht. It then uses iperf3 or netperf to create"
  echo "loads. The output is the goodput in Mbps (unless -D was used)."
  echo ""
  echo "USAGE: $name [out] [-b=<prog>|--bpf=<prog>] [-c=<cc>|--cc=<cc>]"
  echo "             [-D] [-d=<delay>|--delay=<delay>] [--debug] [-E] [--edt]"
  echo "             [-f=<#flows>|--flows=<#flows>] [-h] [-i=<id>|--id=<id >]"
  echo "             [-l] [-N] [--no_cn] [-p=<port>|--port=<port>] [-P]"
  echo "             [-q=<qdisc>] [-R] [-s=<server>|--server=<server]"
  echo "             [-S|--stats] -t=<time>|--time=<time>] [-w] [cubic|dctcp]"
  echo "  Where:"
  echo "    out               egress (default)"
  echo "    -b or --bpf       BPF program filename to load and attach."
  echo "                      Default is hbm_out_kern.o for egress,"
  echo "    -c or -cc         TCP congestion control (cubic or dctcp)"
  echo "    --debug           print BPF trace buffer"
  echo "    -d or --delay     add a delay in ms using netem"
  echo "    -D                In addition to the goodput in Mbps, it also outputs"
  echo "                      other detailed information. This information is"
  echo "                      test dependent (i.e. iperf3 or netperf)."
  echo "    -E                enable ECN (not required for dctcp)"
  echo "    --edt             use fq's Earliest Departure Time (requires fq)"
  echo "    -f or --flows     number of concurrent flows (default=1)"
  echo "    -i or --id        cgroup id (an integer, default is 1)"
  echo "    -N                use netperf instead of iperf3"
  echo "    --no_cn           Do not return CN notifications"
  echo "    -l                do not limit flows using loopback"
  echo "    -h                Help"
  echo "    -p or --port      iperf3 port (default is 5201)"
  echo "    -P                use an iperf3 instance for each flow"
  echo "    -q                use the specified qdisc"
  echo "    -r or --rate      rate in Mbps (default 1s 1Gbps)"
  echo "    -R                Use TCP_RR for netperf. 1st flow has req"
  echo "                      size of 10KB, rest of 1MB. Reply in all"
  echo "                      cases is 1 byte."
  echo "                      More detailed output for each flow can be found"
  echo "                      in the files netperf.<cg>.<flow>, where <cg> is the"
  echo "                      cgroup id as specified with the -i flag, and <flow>"
  echo "                      is the flow id starting at 1 and increasing by 1 for"
  echo "                      flow (as specified by -f)."
  echo "    -s or --server    hostname of netperf server. Used to create netperf"
  echo "                      test traffic between to hosts (default is within host)"
  echo "                      netserver must be running on the host."
  echo "    -S or --stats     whether to update hbm stats (default is yes)."
  echo "    -t or --time      duration of iperf3 in seconds (default=5)"
  echo "    -w                Work conserving flag. cgroup can increase its"
  echo "                      bandwidth beyond the rate limit specified"
  echo "                      while there is available bandwidth. Current"
  echo "                      implementation assumes there is only one NIC"
  echo "                      (eth0), but can be extended to support multiple"
  echo "                       NICs."
  echo "    cubic or dctcp    specify which TCP CC to use"
  echo " "
  exit
}

#set -x

debug_flag=0
args="$@"
name="$0"
netem=0
cc=x
dir="-o"
dir_name="out"
dur=5
flows=1
id=1
prog=""
port=5201
rate=1000
multi_iperf=0
flow_cnt=1
use_netperf=0
rr=0
ecn=0
details=0
server=""
qdisc=""
flags=""
do_stats=0

function start_hbm () {
  rm -f hbm.out
  echo "./hbm $dir -n $id -r $rate -t $dur $flags $dbg $prog" > hbm.out
  echo " " >> hbm.out
  ./hbm $dir -n $id -r $rate -t $dur $flags $dbg $prog >> hbm.out 2>&1  &
  echo $!
}

processArgs () {
  for i in $args ; do
    case $i in
    # Support for upcomming ingress rate limiting
    #in)         # support for upcoming ingress rate limiting
    #  dir="-i"
    #  dir_name="in"
    #  ;;
    out)
      dir="-o"
      dir_name="out"
      ;;
    -b=*|--bpf=*)
      prog="${i#*=}"
      ;;
    -c=*|--cc=*)
      cc="${i#*=}"
      ;;
    --no_cn)
      flags="$flags --no_cn"
      ;;
    --debug)
      flags="$flags -d"
      debug_flag=1
      ;;
    -d=*|--delay=*)
      netem="${i#*=}"
      ;;
    -D)
      details=1
      ;;
    -E)
      ecn=1
      ;;
    --edt)
      flags="$flags --edt"
      qdisc="fq"
     ;;
    -f=*|--flows=*)
      flows="${i#*=}"
      ;;
    -i=*|--id=*)
      id="${i#*=}"
      ;;
    -l)
      flags="$flags -l"
      ;;
    -N)
      use_netperf=1
      ;;
    -p=*|--port=*)
      port="${i#*=}"
      ;;
    -P)
      multi_iperf=1
      ;;
    -q=*)
      qdisc="${i#*=}"
      ;;
    -r=*|--rate=*)
      rate="${i#*=}"
      ;;
    -R)
      rr=1
      ;;
    -s=*|--server=*)
      server="${i#*=}"
      ;;
    -S|--stats)
      flags="$flags -s"
      do_stats=1
      ;;
    -t=*|--time=*)
      dur="${i#*=}"
      ;;
    -w)
      flags="$flags -w"
      ;;
    cubic)
      cc=cubic
      ;;
    dctcp)
      cc=dctcp
      ;;
    *)
      echo "Unknown arg:$i"
      Usage
      ;;
    esac
  done
}

processArgs

if [ $debug_flag -eq 1 ] ; then
  rm -f hbm_out.log
fi

hbm_pid=$(start_hbm)
usleep 100000

host=`hostname`
cg_base_dir=/sys/fs/cgroup
cg_dir="$cg_base_dir/cgroup-test-work-dir/hbm$id"

echo $$ >> $cg_dir/cgroup.procs

ulimit -l unlimited

rm -f ss.out
rm -f hbm.[0-9]*.$dir_name
if [ $ecn -ne 0 ] ; then
  sysctl -w -q -n net.ipv4.tcp_ecn=1
fi

if [ $use_netperf -eq 0 ] ; then
  cur_cc=`sysctl -n net.ipv4.tcp_congestion_control`
  if [ "$cc" != "x" ] ; then
    sysctl -w -q -n net.ipv4.tcp_congestion_control=$cc
  fi
fi

if [ "$netem" -ne "0" ] ; then
  if [ "$qdisc" != "" ] ; then
    echo "WARNING: Ignoring -q options because -d option used"
  fi
  tc qdisc del dev lo root > /dev/null 2>&1
  tc qdisc add dev lo root netem delay $netem\ms > /dev/null 2>&1
elif [ "$qdisc" != "" ] ; then
  tc qdisc del dev eth0 root > /dev/null 2>&1
  tc qdisc add dev eth0 root $qdisc > /dev/null 2>&1
fi

n=0
m=$[$dur * 5]
hn="::1"
if [ $use_netperf -ne 0 ] ; then
  if [ "$server" != "" ] ; then
    hn=$server
  fi
fi

( ping6 -i 0.2 -c $m $hn > ping.out 2>&1 ) &

if [ $use_netperf -ne 0 ] ; then
  begNetserverPid=`ps ax | grep netserver | grep --invert-match "grep" | \
                   awk '{ print $1 }'`
  if [ "$begNetserverPid" == "" ] ; then
    if [ "$server" == "" ] ; then
      ( ./netserver > /dev/null 2>&1) &
      usleep 100000
    fi
  fi
  flow_cnt=1
  if [ "$server" == "" ] ; then
    np_server=$host
  else
    np_server=$server
  fi
  if [ "$cc" == "x" ] ; then
    np_cc=""
  else
    np_cc="-K $cc,$cc"
  fi
  replySize=1
  while [ $flow_cnt -le $flows ] ; do
    if [ $rr -ne 0 ] ; then
      reqSize=1M
      if [ $flow_cnt -eq 1 ] ; then
        reqSize=10K
      fi
      if [ "$dir" == "-i" ] ; then
        replySize=$reqSize
        reqSize=1
      fi
      ( ./netperf -H $np_server -l $dur -f m -j -t TCP_RR  -- -r $reqSize,$replySize $np_cc -k P50_lATENCY,P90_LATENCY,LOCAL_TRANSPORT_RETRANS,REMOTE_TRANSPORT_RETRANS,LOCAL_SEND_THROUGHPUT,LOCAL_RECV_THROUGHPUT,REQUEST_SIZE,RESPONSE_SIZE > netperf.$id.$flow_cnt ) &
    else
      if [ "$dir" == "-i" ] ; then
        ( ./netperf -H $np_server -l $dur -f m -j -t TCP_RR -- -r 1,10M $np_cc -k P50_LATENCY,P90_LATENCY,LOCAL_TRANSPORT_RETRANS,LOCAL_SEND_THROUGHPUT,REMOTE_TRANSPORT_RETRANS,REMOTE_SEND_THROUGHPUT,REQUEST_SIZE,RESPONSE_SIZE > netperf.$id.$flow_cnt ) &
      else
        ( ./netperf -H $np_server -l $dur -f m -j -t TCP_STREAM -- $np_cc -k P50_lATENCY,P90_LATENCY,LOCAL_TRANSPORT_RETRANS,LOCAL_SEND_THROUGHPUT,REQUEST_SIZE,RESPONSE_SIZE > netperf.$id.$flow_cnt ) &
      fi
    fi
    flow_cnt=$[flow_cnt+1]
  done

# sleep for duration of test (plus some buffer)
  n=$[dur+2]
  sleep $n

# force graceful termination of netperf
  pids=`pgrep netperf`
  for p in $pids ; do
    kill -SIGALRM $p
  done

  flow_cnt=1
  rate=0
  if [ $details -ne 0 ] ; then
    echo ""
    echo "Details for HBM in cgroup $id"
    if [ $do_stats -eq 1 ] ; then
      if [ -e hbm.$id.$dir_name ] ; then
        cat hbm.$id.$dir_name
      fi
    fi
  fi
  while [ $flow_cnt -le $flows ] ; do
    if [ "$dir" == "-i" ] ; then
      r=`cat netperf.$id.$flow_cnt | grep -o "REMOTE_SEND_THROUGHPUT=[0-9]*" | grep -o "[0-9]*"`
    else
      r=`cat netperf.$id.$flow_cnt | grep -o "LOCAL_SEND_THROUGHPUT=[0-9]*" | grep -o "[0-9]*"`
    fi
    echo "rate for flow $flow_cnt: $r"
    rate=$[rate+r]
    if [ $details -ne 0 ] ; then
      echo "-----"
      echo "Details for cgroup $id, flow $flow_cnt"
      cat netperf.$id.$flow_cnt
    fi
    flow_cnt=$[flow_cnt+1]
  done
  if [ $details -ne 0 ] ; then
    echo ""
    delay=`grep "avg" ping.out | grep -o "= [0-9.]*/[0-9.]*" | grep -o "[0-9.]*$"`
    echo "PING AVG DELAY:$delay"
    echo "AGGREGATE_GOODPUT:$rate"
  else
    echo $rate
  fi
elif [ $multi_iperf -eq 0 ] ; then
  (iperf3 -s -p $port -1 > /dev/null 2>&1) &
  usleep 100000
  iperf3 -c $host -p $port -i 0 -P $flows -f m -t $dur > iperf.$id
  rates=`grep receiver iperf.$id | grep -o "[0-9.]* Mbits" | grep -o "^[0-9]*"`
  rate=`echo $rates | grep -o "[0-9]*$"`

  if [ $details -ne 0 ] ; then
    echo ""
    echo "Details for HBM in cgroup $id"
    if [ $do_stats -eq 1 ] ; then
      if [ -e hbm.$id.$dir_name ] ; then
        cat hbm.$id.$dir_name
      fi
    fi
    delay=`grep "avg" ping.out | grep -o "= [0-9.]*/[0-9.]*" | grep -o "[0-9.]*$"`
    echo "PING AVG DELAY:$delay"
    echo "AGGREGATE_GOODPUT:$rate"
  else
    echo $rate
  fi
else
  flow_cnt=1
  while [ $flow_cnt -le $flows ] ; do
    (iperf3 -s -p $port -1 > /dev/null 2>&1) &
    ( iperf3 -c $host -p $port -i 0 -P 1 -f m -t $dur | grep receiver | grep -o "[0-9.]* Mbits" | grep -o "^[0-9]*" | grep -o "[0-9]*$" > iperf3.$id.$flow_cnt ) &
    port=$[port+1]
    flow_cnt=$[flow_cnt+1]
  done
  n=$[dur+1]
  sleep $n
  flow_cnt=1
  rate=0
  if [ $details -ne 0 ] ; then
    echo ""
    echo "Details for HBM in cgroup $id"
    if [ $do_stats -eq 1 ] ; then
      if [ -e hbm.$id.$dir_name ] ; then
        cat hbm.$id.$dir_name
      fi
    fi
  fi

  while [ $flow_cnt -le $flows ] ; do
    r=`cat iperf3.$id.$flow_cnt`
#    echo "rate for flow $flow_cnt: $r"
  if [ $details -ne 0 ] ; then
    echo "Rate for cgroup $id, flow $flow_cnt LOCAL_SEND_THROUGHPUT=$r"
  fi
    rate=$[rate+r]
    flow_cnt=$[flow_cnt+1]
  done
  if [ $details -ne 0 ] ; then
    delay=`grep "avg" ping.out | grep -o "= [0-9.]*/[0-9.]*" | grep -o "[0-9.]*$"`
    echo "PING AVG DELAY:$delay"
    echo "AGGREGATE_GOODPUT:$rate"
  else
    echo $rate
  fi
fi

if [ $use_netperf -eq 0 ] ; then
  sysctl -w -q -n net.ipv4.tcp_congestion_control=$cur_cc
fi
if [ $ecn -ne 0 ] ; then
  sysctl -w -q -n net.ipv4.tcp_ecn=0
fi
if [ "$netem" -ne "0" ] ; then
  tc qdisc del dev lo root > /dev/null 2>&1
fi
if [ "$qdisc" != "" ] ; then
  tc qdisc del dev eth0 root > /dev/null 2>&1
fi
sleep 2

hbmPid=`ps ax | grep "hbm " | grep --invert-match "grep" | awk '{ print $1 }'`
if [ "$hbmPid" == "$hbm_pid" ] ; then
  kill $hbm_pid
fi

sleep 1

# Detach any BPF programs that may have lingered
ttx=`bpftool cgroup tree | grep hbm`
v=2
for x in $ttx ; do
    if [ "${x:0:36}" == "/sys/fs/cgroup/cgroup-test-work-dir/" ] ; then
	cg=$x ; v=0
    else
	if [ $v -eq 0 ] ; then
	    id=$x ; v=1
	else
	    if [ $v -eq 1 ] ; then
		type=$x ; bpftool cgroup detach $cg $type id $id
		v=0
	    fi
	fi
    fi
done

if [ $use_netperf -ne 0 ] ; then
  if [ "$server" == "" ] ; then
    if [ "$begNetserverPid" == "" ] ; then
      netserverPid=`ps ax | grep netserver | grep --invert-match "grep" | awk '{ print $1 }'`
      if [ "$netserverPid" != "" ] ; then
        kill $netserverPid
      fi
    fi
  fi
fi
exit