IPv6 UDP Flow with Latency Measurement - invalid UDP checksum
Posted by Mathieu Strubbe, Last modified by Dries Decock on 03 April 2018 02:02 PM
You probably arrived at this page after clicking on an Info Item in a ByteBlower Report looking like this one:
This article explains what this means.
What happened ?
The test scenario you just executed contains a flow, sending IPv6 UDP Frames with the Automatic Checksum enabled on the Layer 4 tab in the Frame View.
On top of that, the Latency Measurement option was enabled for this flow. To be able to measure the latency, a timestamp value is inserted at the end of each Frame. Of course, this makes the UDP checksum invalid.
So, after setting the timestamp, the UDP checksum should be re-calculated automatically. But on some ByteBlower servers, this is not possible. Due to limitations of the hardware used inside the ByteBlower server, it is not possible to send Frames with a timestamp and a correct UDP checksum.
Because the UDP checksum is required in IPv6 Frames, we cannot apply the same workaround as for IPv4 frames. (setting the checksum value automatically to zero, which means that the checksum is disabled.)
This way, the IPv6 frames sent out by the ByteBlower server will have an invalid UDP checksum. Some devices in your test setup may drop these frames.
For more technical details about this issue, check out this article: Known Issue: 100% packetloss on latency measurements 2x00/4x00 series
So, should I be worried ?
This issue may cause 100% packet loss because devices in your test setup may drop the frames with an incorrect IPv6 UDP checksum.
Otherwise, the results displayed in the report are perfectly valid.