Allow measuring ping latency and CPU details at idle as a baseline before
measuring under data transfer loading. This allows better determination of
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.
Change the default test duration to 30 seconds, which is adequate for SQM
tuning while reducing bandwidth consumption for upstream netperf servers.
Change the default ping host from gstatic.com to one.one.one.one, which is
widely available and generally shows lower latency.
When warning of internal netperf errors, suggest running netperf directly
to view error details.
Other minor updates include:
- clear tmp file names for safety in case of traps
- simplify ping code, argument parsing and number validation
- fix cases of wrong protocol usage with hostname as ping target
- drop unneeded egrep usage
Also update README accordingly, with clearer usage text and terminology.
Signed-off-by: Tony Ambardar <itugrok@yahoo.com>
The speedtest-netperf.sh script measures the network throughput while
monitoring latency under load and capturing key CPU usage and frequency
statistics. The script can emulate a web-based speed test by downloading
and then uploading from an internet server, or perform simultaneous
download and upload to mimic the stress of the FLENT test program.
It simplifies tasks such as validating ISP provisioned speeds or setting
up and fine-tuning SQM, directly on the router. The CPU usage details
can also help determine if the demands of SQM, routing and other tasks
such as the test itself are exhausting the device's CPUs.
This script leverages earlier scripts from the CeroWrt project used for
bufferbloat mitigation, betterspeedtest.sh and netperfrunner.sh. They are
used with the permission of the author, Rich Brown.
Signed-off-by: Tony Ambardar <itugrok@yahoo.com>
Tony Ambardar