On 23 September 2012 19:28, Michael Hudson-Doyle michael.hudson@linaro.org wrote:
Zach Pfeffer zach.pfeffer@linaro.org writes:
Just wanted to share this with everyone.
I've attached the "output" folder that the NI instrument creates for each test session. In the results file you'll see a text doc called results.txt that lists the comma delimited parameters that get measured followed by the measurements themselves:
Current Cycle Average,Current Cycle RMS,Current Mean (DC),Current Negative Peak,Current Peak to Peak,Current Positive Peak,Current RMS,Volt Cycle Average,Volt Cycle RMS,Volt Mean (DC),Volt Negative Peak,Volt Peak to Peak,Volt Positive Peak,Volt RMS
See:
https://docs.google.com/a/linaro.org/file/d/0B3pUtxWjZbP9bFhqNGZfYzNSMWs/edi...
That actually looks fairly similar to what you get out of streamline with the energy probe. Not too surprising I guess.
Included in each record is a Record Number that indexes into the "report directory." Each directory is marked with an index and under that directory is the graph associated with the data for example:
https://docs.google.com/a/linaro.org/file/d/0B3pUtxWjZbP9VnVQS3M4WWx1OVk/edi...
In addition, controlling the instrument is super easy. You connect to the box over TCP/IP the you can send 5 single character commands in any order: 1,0,s,e,r
1 turns the power on 0 turns it off s starts a measurement e ends a measurement r records
r is destructive, so if you send an r it erase the previous data record. The data record does survive instrument restarts (as opposed to having an implicit r at the start of the measurement.
I'm not sure I entirely understand. What's the difference between "r" and "s", aside from the fact that r erases previous data?
r clears the previous run's data and gets the files ready for the next runs.
s just starts the measurement, its a software trigger, e ends the measurement you can say s and e multiple times. Each time an entry gets made into the readings.txt file and a graph capture gets made.
Is there any reason to power the device down between tests in the usual course of things?
Not sure, but it may prove a useful thing to do. We have been power cycling between lava tests to improve reproducibility so i suspect power tests may need the same feature.
At any point the existing data set can simply be uploaded.
This is just putting things into my language rather than yours I guess, but is it correct to stay that your VI puts the output in a known location, so other processes on the box can access it?
Actually, the idea is for LAVA to upload the data set via FTP. I'm also going to add a z command which will zip up the data set. They'll be FTP running on the box (or whatever we need) and LAVA will just transfer the files and save them with the test run.
I'm imagining something like the following course of events during a test run (please forgive a certain amount of hand-waving):
- The LAVA host sends '1' if necessary to the VI and then 'r'
- for each test case:
- The target sends 's' to the VI
- The target runs the test case
- The target send 'e' to the VI
- The LAVA host grabs the results from the VI and matches the power data against the test results
- The host (maybe?) sends '0' to the VI.
- The results are uploaded to the dashboard and displayed in some useful way
Yeah, that's basically it.
One minor point. This instrument produces a lot of data, instead of moving all this data around, the instrument can be configured to do all the measurement, making the analyzed data set easier to understand and faster to upload.
Yeah, I think that we'd like to just upload something like the readings.txt file for now? Or possibly something even more derived than that to start with... just the average power draw over a period would be a good start!
Take a look at the readings.txt the figure of merit is the RMS Current. That's what you should display. Voltage is more or less constant, though I also present the RMS voltage. But you'll want to actually show all the numbers in there.
Comments and questions welcome.
See it in action at: https://plus.google.com/u/0/104422661029399872488/posts/NU4pZ36L13U
Cheers, mwh