3. **CPU Usage:** Observing CPU usage under network load gives insight into whether the router is CPU-bound, or if there is CPU "headroom" to support even higher network throughput. In addition to managing network traffic, a router actively running a speed test will also use CPU cycles to generate network load, and measuring this distinct CPU usage also helps gauge its impact.
-**Note:** _The `speedtest-netperf.sh` script uses servers and network bandwidth that are provided by generous volunteers (not some wealthy "big company"). Feel free to use the script to test your SQM configuration or troubleshoot network and latency problems. Continuous or high rate use of this script may result in denied access. Happy testing!_
+**Note:** _The `speedtest-netperf.sh` script uses servers and network bandwidth that are provided by generous volunteers. Feel free to use the script to test your SQM configuration or troubleshoot network and latency problems, but be warned that continuous or high-rate use of the servers may result in denied access. Happy testing!_
## Theory of Operation
Concurrent mode places greater stress on the network, and can expose additional latency problems. It provides a more realistic estimate of expected bidirectional throughput. However, the download and upload speeds reported may be considerably lower than your line's rated speed. This is not a bug, nor is it a problem with your internet connection. It's because the ACK (acknowledge) messages sent back to the sender may consume a significant fraction of a link's capacity (as much as 50% with highly asymmetric links, e.g 15:1 or 20:1).
+The script also supports measuring latency when idle as a baseline prior to measuring under network load. This allows better determination of induced latency under load, a critical bufferbloat parameter. The CPU details can also be used to verify idle conditions or examine CPU frequency against ping variations and jitter (e.g. tracing high jitter to occasional low CPU frequency operation).
+
After running `speedtest-netperf.sh`, if latency is seen to increase much during the data transfers, then other network activity, such as voice or video chat, gaming, and general interactive usage will likely suffer. Gamers will see this as frustrating lag when someone else uses the network, Skype and FaceTime users will see dropouts or freezes, and VOIP service may be unusable.
## Installation
## Usage
-The speedtest-netperf.sh script measures throughput, latency and CPU usage during file transfers. To invoke it:
+The speedtest-netperf.sh script measures throughput, latency and CPU usage during file transfers and when idle. To invoke it:
- speedtest-netperf.sh [-4 | -6] [-H netperf-server] [-t duration] [-p host-to-ping] [-n simultaneous-streams ] [-s | -c]
+ speedtest-netperf.sh [-4 | -6] [-H netperf-server] [-t duration] [-p host-to-ping] [-n simultaneous-streams ] [-s | -c [duration] ] [ -i [duration] ]
Options, if present, are:
-H | --host: DNS or Address of a netperf server (default - netperf.bufferbloat.net)
Alternate servers are netperf-east (US, east coast),
netperf-west (US, California), and netperf-eu (Denmark).
- -t | --time: Duration for how long each direction's test should run - (default - 60 seconds)
- -p | --ping: Host to ping to measure latency (default - gstatic.com)
+ -t | --time: Duration for how long each direction's test should run - (default - 30 seconds)
+ -p | --ping: Host to ping to measure latency (default - one.one.one.one)
-n | --number: Number of simultaneous sessions (default - 5 sessions)
- -s | --sequential: Sequential download/upload (default - sequential)
- -c | --concurrent: Concurrent download/upload
+ -s | --sequential: Sequential download/upload (default - disabled)
+ -c | --concurrent: Concurrent download/upload (default - disabled)
+ -i | --idle: Measure idle latency before speed test (default - disabled)
The primary script output shows download and upload speeds, together with the percent packet loss, and a summary of latencies, including min, max, average, median, and 10th and 90th percentiles so you can get a sense of the distribution.
```
[Sequential Test: NO SQM, POOR LATENCY] [Sequential Test: WITH SQM, GOOD LATENCY]
-# speedtest-netperf.sh # speedtest-netperf.sh
+# speedtest-netperf.sh --sequential # speedtest-netperf.sh --sequential
[date/time] Starting speedtest for 60 seconds per transfer [date/time] Starting speedtest for 60 seconds per transfer
session. Measure speed to netperf.bufferbloat.net (IPv4) session. Measure speed to netperf.bufferbloat.net (IPv4)
while pinging gstatic.com. Download and upload sessions are while pinging gstatic.com. Download and upload sessions are
# first downloading and then uploading network streams, while concurrent mode
# provides a stress test by dowloading and uploading streams simultaneously.
#
+# The script also supports measuring latency when idle as a baseline prior to
+# testing under network load.
+#
# NOTE: The script uses servers and network bandwidth that are provided by
-# generous volunteers (not some wealthy "big company"). Feel free to use the
-# script to test your SQM configuration or troubleshoot network and latency
-# problems. Continuous or high rate use of this script may result in denied
-# access. Happy testing!
+# generous volunteers. Feel free to use the script to test your SQM
+# configuration or troubleshoot network and latency problems, but be warned
+# that continuous or high-rate use of the servers may result in denied access.
+# Happy testing!
#
# For more information, consult the online README.md:
# https://github.com/openwrt/packages/blob/master/net/speedtest-netperf/files/README.md
-# Usage: speedtest-netperf.sh [-4 | -6] [ -H netperf-server ] [ -t duration ] [ -p host-to-ping ] [ -n simultaneous-streams ] [ -s | -c ]
+# Usage: speedtest-netperf.sh [-4 | -6] [ -H netperf-server ] [ -t duration ] [ -p host-to-ping ] [ -n simultaneous-streams ] [ -s | -c [duration] ] [ -i [duration] ]
# Options: If options are present:
#
# Alternate servers are netperf-east (east coast US),
# netperf-west (California), and netperf-eu (Denmark)
# -4 | -6: Enable ipv4 or ipv6 testing (ipv4 is the default)
-# -t | --time: Duration of each direction's test - (default - 60 seconds)
-# -p | --ping: Host to ping to measure latency (default - gstatic.com)
-# -n | --number: Number of simultaneous sessions (default - 5 sessions)
+# -t | --time: Duration of each direction's test - (default - 30 seconds)
+# -p | --ping: Host to ping to measure latency (default - one.one.one.one)
+# -n | --number: Number of simultaneous streams (default - 5 streams)
# based on whether concurrent or sequential upload/downloads)
-# -s | -c: Sequential or concurrent download/upload (default - sequential)
+# -s | -c: Sequential or concurrent download/upload (default - disabled)
+# -i | --idle: Measure idle latency before speed test (default - disabled)
# Copyright (c) 2014 - Rich Brown <rich.brown@blueberryhillsoftware.com>
-# Copyright (c) 2018 - Tony Ambardar <itugrok@yahoo.com>
+# Copyright (c) 2018-2024 - Tony Ambardar <itugrok@yahoo.com>
# GPLv2
cat /proc/$$/stat
while : ; do
sleep 1s
- egrep "^cpu[0-9]*" /proc/stat
+ grep "^cpu[0-9]*" /proc/stat
for c in $cpus; do
[ -r $c/$f ] && echo "cpufreq $(basename $c) $(cat $c/$f)"
done
done
}
-# Start $MAXSESSIONS datastreams between netperf client and server
+# Start $MAXSTREAMS datastreams between netperf client and server
# netperf writes the sole output value (in Mbps) to stdout when completed
start_netperf() {
- for i in $( seq $MAXSESSIONS ); do
- netperf $TESTPROTO -H $TESTHOST -t $1 -l $TESTDUR -v 0 -P 0 >> $2 &
-# echo "Starting PID $! params: $TESTPROTO -H $TESTHOST -t $1 -l $TESTDUR -v 0 -P 0 >> $2"
+ for i in $( seq $MAXSTREAMS ); do
+ netperf $TESTPROTO -H $TESTHOST -t $1 -l $SPEEDDUR -v 0 -P 0 >> $2 &
+# echo "Starting PID $! params: $TESTPROTO -H $TESTHOST -t $1 -l $SPEEDDUR -v 0 -P 0 >> $2"
done
}
exit 1
}
+# Measure ping latency at idle as a baseline for comparison.
+
+measure_idle() {
+
+ # Create temp files for netperf up/download results
+ PINGFILE=$(mktemp /tmp/measurepings.XXXXXX) || exit 1
+ LOADFILE=$(mktemp /tmp/measureload.XXXXXX) || exit 1
+# echo $PINGFILE $LOADFILE
+
+ # Start dots
+ print_dots &
+ DOTS_PID=$!
+# echo "Dots PID: $DOTS_PID"
+
+ # Start Ping
+ ping $TESTPROTO $PINGHOST > $PINGFILE &
+ PING_PID=$!
+# echo "Ping PID: $PING_PID"
+
+ # Start CPU load sampling
+ sample_load > $LOADFILE &
+ LOAD_PID=$!
+# echo "Load PID: $LOAD_PID"
+
+ # Wait for idle test period
+ sleep $IDLEDUR
+
+ # When idle time elapses, stop the CPU monitor, dots and pings
+ kill_load
+ kill_pings
+ kill_dots
+ echo
+
+ # Summarize the ping data
+ summarize_pings $PINGFILE
+
+ # Summarize the load data
+ summarize_load $LOADFILE
+
+ # Clean up
+ rm -f $PINGFILE
+ rm -f $LOADFILE
+}
+
# Measure speed, ping latency and cpu usage of netperf data transfers
# Called with direction parameter: "Download", "Upload", or "Bidirectional"
# The function gets other info from globals and command-line arguments.
# echo "Dots PID: $DOTS_PID"
# Start Ping
- if [ $TESTPROTO -eq "-4" ]; then
- ping $PINGHOST > $PINGFILE &
- else
- ping6 $PINGHOST > $PINGFILE &
- fi
+ ping $TESTPROTO $PINGHOST > $PINGFILE &
PING_PID=$!
# echo "Ping PID: $PING_PID"
# Wait until background netperf processes complete, check errors
if ! wait_netperf; then
- echo;echo "WARNING: netperf returned errors. Results may be inaccurate!"
+ echo
+ echo "WARNING: Results may be inaccurate since 'netperf' returned errors."
+ echo " Run directly for more details:"
+ echo " netperf $TESTPROTO -H $TESTHOST"
fi
# When netperf completes, stop the CPU monitor, dots and pings
rm -f $LOADFILE
}
+print_usage() {
+ echo \
+"Usage: speedtest-netperf.sh [ -H netperf-server ] [ -p host-to-ping ] [-4 | -6]
+ [ -i [duration] ] [ -s | -c [duration] ]
+ [ -t duration ] [ -n simultaneous-streams ]"
+}
+
+is_number() {
+ case "$1" in
+ ""|*[![:digit:]]*) return 1;;
+ *) return 0 ;;
+ esac
+}
+
# ------- Start of the main routine --------
-# set an initial values for defaults
+# Set initial values for defaults
TESTHOST="netperf.bufferbloat.net"
-TESTDUR="60"
-PINGHOST="gstatic.com"
-MAXSESSIONS=5
+PINGHOST="one.one.one.one"
+MAXSTREAMS=5
TESTPROTO="-4"
-TESTSEQ=1
-
-# read the options
-
-# extract options and their arguments into variables.
+TESTSPEED=0
+SPEEDDUR="30"
+TESTIDLE=0
+IDLEDUR="30"
+
+# Clear temp files
+DLFILE=
+ULFILE=
+PINGFILE=
+LOADFILE=
+
+# Parse options and their parameters into variables. Options for --idle,
+# --sequential and --concurrent have optional parameters.
while [ $# -gt 0 ]
do
case "$1" in
- -s|--sequential) TESTSEQ=1 ; shift 1 ;;
- -c|--concurrent) TESTSEQ=0 ; shift 1 ;;
+ -i|--idle)
+ TESTIDLE=1 ; shift 1
+ is_number "$1" && { IDLEDUR=$1 ; shift 1 ; } ;;
+ -s|--sequential)
+ TESTSPEED=1 ; shift 1
+ is_number "$1" && { SPEEDDUR=$1 ; shift 1 ; } ;;
+ -c|--concurrent)
+ TESTSPEED=2 ; shift 1
+ is_number "$1" && { SPEEDDUR=$1 ; shift 1 ; } ;;
-4|-6) TESTPROTO=$1 ; shift 1 ;;
-H|--host)
case "$2" in
"") echo "Missing hostname" ; exit 1 ;;
- *) TESTHOST=$2 ; shift 2 ;;
+ *) TESTHOST="$2" ; shift 2 ;;
esac ;;
-t|--time)
- case "$2" in
- "") echo "Missing duration" ; exit 1 ;;
- *) TESTDUR=$2 ; shift 2 ;;
- esac ;;
+ is_number "$2" || { echo "Missing duration" ; exit 1 ; }
+ IDLEDUR=$2 ; SPEEDDUR=$2 ; shift 2 ;;
-p|--ping)
case "$2" in
"") echo "Missing ping host" ; exit 1 ;;
*) PINGHOST=$2 ; shift 2 ;;
esac ;;
-n|--number)
- case "$2" in
- "") echo "Missing number of simultaneous streams" ; exit 1 ;;
- *) MAXSESSIONS=$2 ; shift 2 ;;
- esac ;;
+ is_number $2 || { echo "Missing number of streams" ; exit 1 ; }
+ MAXSTREAMS=$2 ; shift 2 ;;
--) shift ; break ;;
- *) echo "Usage: speedtest-netperf.sh [ -s | -c ] [-4 | -6] [ -H netperf-server ] [ -t duration ] [ -p host-to-ping ] [ -n simultaneous-sessions ]" ; exit 1 ;;
+ *) print_usage ; exit 1 ;;
esac
done
+# Extra argument validations
+
+if [ $TESTIDLE -eq "0" ] && [ $TESTSPEED -eq "0" ]; then
+ echo "Please select an idle latency test and/or speed test:"
+ print_usage ; exit 1
+fi
+
# Check dependencies
if ! netperf -V >/dev/null 2>&1; then
echo "Missing netperf program, please install" ; exit 1
fi
-# Start the main test
+# Catch a Ctl-C and stop background netperf, CPU stats, pinging and print_dots
+trap kill_background_and_exit HUP INT TERM
+
+# Start the main tests
DATE=$(date "+%Y-%m-%d %H:%M:%S")
-echo "$DATE Starting speedtest for $TESTDUR seconds per transfer session."
-echo "Measure speed to $TESTHOST (IPv${TESTPROTO#-}) while pinging $PINGHOST."
-echo -n "Download and upload sessions are "
-[ "$TESTSEQ " -eq "1" ] && echo -n "sequential," || echo -n "concurrent,"
-echo " each with $MAXSESSIONS simultaneous streams."
+echo -n "$DATE Begin test with "
+[ $TESTIDLE -eq "1" ] && echo -n "$IDLEDUR-second ping"
+[ $(($TESTIDLE * $TESTSPEED)) -ne "0" ] && echo -n ", "
+[ $TESTSPEED -ne "0" ] && echo -n "$SPEEDDUR-second transfer"
+echo " sessions."
+
+if [ $TESTIDLE -eq "1" ]; then
+ echo "Measure idle latency by pinging $PINGHOST (IPv${TESTPROTO#-})."
+ measure_idle
+ echo
+fi
-# Catch a Ctl-C and stop background netperf, CPU stats, pinging and print_dots
-trap kill_background_and_exit HUP INT TERM
+if [ $TESTSPEED -ne "0" ]; then
+ echo "Measure speed to $TESTHOST (IPv${TESTPROTO#-}) while pinging $PINGHOST."
+ echo -n "Download and upload sessions are "
+ [ "$TESTSPEED" -eq "1" ] && echo -n "sequential," || echo -n "concurrent,"
+ echo " each with $MAXSTREAMS simultaneous streams."
-if [ $TESTSEQ -eq "1" ]; then
- measure_direction "Download"
- measure_direction "Upload"
-else
- measure_direction "Bidirectional"
+ if [ $TESTSPEED -eq "1" ]; then
+ measure_direction "Download"
+ measure_direction "Upload"
+ else
+ measure_direction "Bidirectional"
+ fi
fi
projects / feed / packages.git / commitdiff