|
|
1 - LOOPBACK DRIVER
|
|
The driver implements the main logic of the loopback test and provides
|
sysfs files to configure the test and retrieve the results.
|
A user could run a test without the need of the test application given
|
that he understands the sysfs interface of the loopback driver.
|
|
The loopback kernel driver needs to be loaded and at least one module
|
with the loopback feature enabled must be present for the sysfs files to be
|
created and for the loopback test application to be able to run.
|
|
To load the module:
|
# modprobe gb-loopback
|
|
|
When the module is probed, New files are available on the sysfs
|
directory of the detected loopback device.
|
(typically under "/sys/bus/graybus/devices").
|
|
Here is a short summary of the sysfs interface files that should be visible:
|
|
* Loopback Configuration Files:
|
async - Use asynchronous operations.
|
iteration_max - Number of tests iterations to perform.
|
size - payload size of the transfer.
|
timeout - The number of microseconds to give an individual
|
asynchronous request before timing out.
|
us_wait - Time to wait between 2 messages
|
type - By writing the test type to this file, the test starts.
|
Valid tests are:
|
0 stop the test
|
2 - ping
|
3 - transfer
|
4 - sink
|
|
* Loopback feedback files:
|
error - number of errors that have occurred.
|
iteration_count - Number of iterations performed.
|
requests_completed - Number of requests successfully completed.
|
requests_timedout - Number of requests that have timed out.
|
timeout_max - Max allowed timeout
|
timeout_min - Min allowed timeout.
|
|
* Loopback result files:
|
apbridge_unipro_latency_avg
|
apbridge_unipro_latency_max
|
apbridge_unipro_latency_min
|
gpbridge_firmware_latency_avg
|
gpbridge_firmware_latency_max
|
gpbridge_firmware_latency_min
|
requests_per_second_avg
|
requests_per_second_max
|
requests_per_second_min
|
latency_avg
|
latency_max
|
latency_min
|
throughput_avg
|
throughput_max
|
throughput_min
|
|
|
|
2 - LOOPBACK TEST APPLICATION
|
|
The loopback test application manages and formats the results provided by
|
the loopback kernel module. The purpose of this application
|
is to:
|
- Start and manage multiple loopback device tests concurrently.
|
- Calculate the aggregate results for multiple devices.
|
- Gather and format test results (csv or human readable).
|
|
The best way to get up to date usage information for the application is
|
usually to pass the "-h" parameter.
|
Here is the summary of the available options:
|
|
Mandatory arguments
|
-t must be one of the test names - sink, transfer or ping
|
-i iteration count - the number of iterations to run the test over
|
Optional arguments
|
-S sysfs location - location for greybus 'endo' entries default /sys/bus/greybus/devices/
|
-D debugfs location - location for loopback debugfs entries default /sys/kernel/debug/gb_loopback/
|
-s size of data packet to send during test - defaults to zero
|
-m mask - a bit mask of connections to include example: -m 8 = 4th connection -m 9 = 1st and 4th connection etc
|
default is zero which means broadcast to all connections
|
-v verbose output
|
-d debug output
|
-r raw data output - when specified the full list of latency values are included in the output CSV
|
-p porcelain - when specified printout is in a user-friendly non-CSV format. This option suppresses writing to CSV file
|
-a aggregate - show aggregation of all enabled devies
|
-l list found loopback devices and exit.
|
-x Async - Enable async transfers.
|
-o Timeout - Timeout in microseconds for async operations.
|
|
|
|
3 - REAL WORLD EXAMPLE USAGES
|
|
3.1 - Using the driver sysfs files to run a test on a single device:
|
|
* Run a 1000 transfers of a 100 byte packet. Each transfer is started only
|
after the previous one finished successfully:
|
echo 0 > /sys/bus/greybus/devices/1-2.17/type
|
echo 0 > /sys/bus/greybus/devices/1-2.17/async
|
echo 2000 > /sys/bus/greybus/devices/1-2.17/us_wait
|
echo 100 > /sys/bus/greybus/devices/1-2.17/size
|
echo 1000 > /sys/bus/greybus/devices/1-2.17/iteration_max
|
echo 0 > /sys/bus/greybus/devices/1-2.17/mask
|
echo 200000 > /sys/bus/greybus/devices/1-2.17/timeout
|
echo 3 > /sys/bus/greybus/devices/1-2.17/type
|
|
* Run a 1000 transfers of a 100 byte packet. Transfers are started without
|
waiting for the previous one to finish:
|
echo 0 > /sys/bus/greybus/devices/1-2.17/type
|
echo 3 > /sys/bus/greybus/devices/1-2.17/async
|
echo 0 > /sys/bus/greybus/devices/1-2.17/us_wait
|
echo 100 > /sys/bus/greybus/devices/1-2.17/size
|
echo 1000 > /sys/bus/greybus/devices/1-2.17/iteration_max
|
echo 0 > /sys/bus/greybus/devices/1-2.17/mask
|
echo 200000 > /sys/bus/greybus/devices/1-2.17/timeout
|
echo 3 > /sys/bus/greybus/devices/1-2.17/type
|
|
* Read the results from sysfs:
|
cat /sys/bus/greybus/devices/1-2.17/requests_per_second_min
|
cat /sys/bus/greybus/devices/1-2.17/requests_per_second_max
|
cat /sys/bus/greybus/devices/1-2.17/requests_per_second_avg
|
|
cat /sys/bus/greybus/devices/1-2.17/latency_min
|
cat /sys/bus/greybus/devices/1-2.17/latency_max
|
cat /sys/bus/greybus/devices/1-2.17/latency_avg
|
|
cat /sys/bus/greybus/devices/1-2.17/apbridge_unipro_latency_min
|
cat /sys/bus/greybus/devices/1-2.17/apbridge_unipro_latency_max
|
cat /sys/bus/greybus/devices/1-2.17/apbridge_unipro_latency_avg
|
|
cat /sys/bus/greybus/devices/1-2.17/gpbridge_firmware_latency_min
|
cat /sys/bus/greybus/devices/1-2.17/gpbridge_firmware_latency_max
|
cat /sys/bus/greybus/devices/1-2.17/gpbridge_firmware_latency_avg
|
|
cat /sys/bus/greybus/devices/1-2.17/error
|
cat /sys/bus/greybus/devices/1-2.17/requests_completed
|
cat /sys/bus/greybus/devices/1-2.17/requests_timedout
|
|
|
3.2 - using the test application:
|
|
* Run a transfer test 10 iterations of size 100 bytes on all available devices
|
#/loopback_test -t transfer -i 10 -s 100
|
1970-1-1 0:10:7,transfer,1-4.17,100,10,0,443,509,471.700012,66,1963,2256,2124.600098,293,102776,118088,109318.898438,15312,1620,1998,1894.099976,378,56,57,56.799999,1
|
1970-1-1 0:10:7,transfer,1-5.17,100,10,0,399,542,463.399994,143,1845,2505,2175.800049,660,92568,125744,107393.296875,33176,1469,2305,1806.500000,836,56,57,56.799999,1
|
|
|
* Show the aggregate results of both devices. ("-a")
|
#/loopback_test -t transfer -i 10 -s 100 -a
|
1970-1-1 0:10:35,transfer,1-4.17,100,10,0,448,580,494.100006,132,1722,2230,2039.400024,508,103936,134560,114515.703125,30624,1513,1980,1806.900024,467,56,57,57.299999,1
|
1970-1-1 0:10:35,transfer,1-5.17,100,10,0,383,558,478.600006,175,1791,2606,2115.199951,815,88856,129456,110919.703125,40600,1457,2246,1773.599976,789,56,57,57.099998,1
|
1970-1-1 0:10:35,transfer,aggregate,100,10,0,383,580,486.000000,197,1722,2606,2077.000000,884,88856,134560,112717.000000,45704,1457,2246,1789.000000,789,56,57,57.000000,1
|
|
* Example usage of the mask option to select which devices will
|
run the test (1st, 2nd, or both devices):
|
# /loopback_test -t transfer -i 10 -s 100 -m 1
|
1970-1-1 0:11:56,transfer,1-4.17,100,10,0,514,558,544.900024,44,1791,1943,1836.599976,152,119248,129456,126301.296875,10208,1600,1001609,101613.601562,1000009,56,57,56.900002,1
|
# /loopback_test -t transfer -i 10 -s 100 -m 2
|
1970-1-1 0:12:0,transfer,1-5.17,100,10,0,468,554,539.000000,86,1804,2134,1859.500000,330,108576,128528,124932.500000,19952,1606,1626,1619.300049,20,56,57,57.400002,1
|
# /loopback_test -t transfer -i 10 -s 100 -m 3
|
1970-1-1 0:12:3,transfer,1-4.17,100,10,0,432,510,469.399994,78,1959,2313,2135.800049,354,100224,118320,108785.296875,18096,1610,2024,1893.500000,414,56,57,57.200001,1
|
1970-1-1 0:12:3,transfer,1-5.17,100,10,0,404,542,468.799988,138,1843,2472,2152.500000,629,93728,125744,108646.101562,32016,1504,2247,1853.099976,743,56,57,57.099998,1
|
|
* Show output in human readable format ("-p")
|
# /loopback_test -t transfer -i 10 -s 100 -m 3 -p
|
|
1970-1-1 0:12:37
|
test: transfer
|
path: 1-4.17
|
size: 100
|
iterations: 10
|
errors: 0
|
async: Disabled
|
requests per-sec: min=390, max=547, average=469.299988, jitter=157
|
ap-throughput B/s: min=90480 max=126904 average=108762.101562 jitter=36424
|
ap-latency usec: min=1826 max=2560 average=2146.000000 jitter=734
|
apbridge-latency usec: min=1620 max=1982 average=1882.099976 jitter=362
|
gpbridge-latency usec: min=56 max=57 average=57.099998 jitter=1
|
|
|
1970-1-1 0:12:37
|
test: transfer
|
path: 1-5.17
|
size: 100
|
iterations: 10
|
errors: 0
|
async: Disabled
|
requests per-sec: min=397, max=538, average=461.700012, jitter=141
|
ap-throughput B/s: min=92104 max=124816 average=106998.898438 jitter=32712
|
ap-latency usec: min=1856 max=2514 average=2185.699951 jitter=658
|
apbridge-latency usec: min=1460 max=2296 average=1828.599976 jitter=836
|
gpbridge-latency usec: min=56 max=57 average=57.099998 jitter=1
|
