Difference between revisions of "RTWG-discussion-points"

From eLinux.org
Jump to: navigation, search
 
Line 10: Line 10:
 
* 2-machine system gives unbiased timing results
 
* 2-machine system gives unbiased timing results
 
** instrumentation does not interfere with the timings
 
** instrumentation does not interfere with the timings
 +
 +
=== realfeel ===
 +
benefits:
 +
* is one-machine
 +
* uses /dev/rtc, does not use timer interrupt
 +
** this isolates the ISR handling from timer operations
 +
* is a very simple test
 +
 +
problems:
 +
* uses TSC, which is i386-specific
 +
* doesn't have an instrumentation point in the kernel
 +
** no measurement of int latency, only process start latency
 +
* process start latency is "guessed" from expected interrupt time
 +
** that is, it is not actually measured
 +
* not all boards have a working /dev/rtc driver
 +
 +
 +
=== igel test ===
 +
This tests scheduling latency on receipt of a character on an SM501 uart.
 +
The UART driver gets a timestamp on ISR start, and can be asked for them
 +
from user-space after a run.
 +
The user-space driver measures the time from ISR start to task start.
 +
Test is specific to SH architecture.
 +
Uses SH hardware timer.
 +
 +
See http://tree.celinuxforum.org/CelfPubWiki/UserLevelDeviceDriver
 +
(page is in Japanese)
 +
* Yung Joon will ask Takao Ikoma to translate this page.
 +
* Matsubara-san will update the driver and some of the text on the page.
 +
** will attach latest driver source
 +
* Tim will provide Ikoma-san e-mail

Revision as of 02:03, 4 September 2007

Review of test programs

lpptest

problems:

  • requires 2 machines
  • requires parallel port (not many embedded boards have this)
  • uses TSC, which is i386-specific

benefits:

  • built into the rt-preempt patch
  • 2-machine system gives unbiased timing results
    • instrumentation does not interfere with the timings

realfeel

benefits:

  • is one-machine
  • uses /dev/rtc, does not use timer interrupt
    • this isolates the ISR handling from timer operations
  • is a very simple test

problems:

  • uses TSC, which is i386-specific
  • doesn't have an instrumentation point in the kernel
    • no measurement of int latency, only process start latency
  • process start latency is "guessed" from expected interrupt time
    • that is, it is not actually measured
  • not all boards have a working /dev/rtc driver


igel test

This tests scheduling latency on receipt of a character on an SM501 uart. The UART driver gets a timestamp on ISR start, and can be asked for them from user-space after a run. The user-space driver measures the time from ISR start to task start. Test is specific to SH architecture. Uses SH hardware timer.

See http://tree.celinuxforum.org/CelfPubWiki/UserLevelDeviceDriver (page is in Japanese)

  • Yung Joon will ask Takao Ikoma to translate this page.
  • Matsubara-san will update the driver and some of the text on the page.
    • will attach latest driver source
  • Tim will provide Ikoma-san e-mail