diff options
author | Luc Provoost <luc.provoost@intel.com> | 2020-09-16 09:52:06 +0200 |
---|---|---|
committer | Luc Provoost <luc.provoost@intel.com> | 2020-09-16 09:52:06 +0200 |
commit | d092ffd38f9b5acafb740da11b5a2467ff972036 (patch) | |
tree | 0392e098d0521566fa557601035d848411f71f1d /VNFs/DPPD-PROX/helper-scripts/rapid/l2zeroloss.test | |
parent | 1edebebda08242170aaffba43cfb0747ded2fc76 (diff) |
ramp generator traffic & prox.log copy
A new parameter can be put in the *.test files so that the requested
traffic is not generated at once, but slowly increasing up to the
requested traffic. This is important for some SW switched that adapt and
learn from the applied traffic. When suddenly applying a high traffic,
the switch might not have enough time to learn and lose packets. Only
after a period of time (up to 10 seconds?), the switch can cope with the
traffic without packet loss. In order to get reproducible results in
this case with low packet loss, please put the parameter ramp_step in
the test section of the *.test file. The step is expressed in percentage
of a 10Gb/s traffic. If the parameter is not present, the load will be
immediately applied.
When the runrapid.py script is now finished, it also copies the prox.log
files from all the prox instances. In case of issues, please investigate
this log file.
When using background traffic, the tool will also print the average
background traffic for each step in the DEBUG log. In this way, you can
check that the background traffic is actually dealing with the same
amount of traffic as the foreground. The tool is printing the packet
reception rate of the background generators.
A bug was also fixed regarding the latency percentile reporting. When
using tests involving l2gen.cfg, the values of the percentile latency
were wrong.
Change-Id: Id3dd02ed5cab084414c717cf898b30e6980ddf31
Signed-off-by: Luc Provoost <luc.provoost@intel.com>
Diffstat (limited to 'VNFs/DPPD-PROX/helper-scripts/rapid/l2zeroloss.test')
0 files changed, 0 insertions, 0 deletions