RTAI Testsuite LiveCD

Hardware

CPU

name	value
CPU name:	(R) Pentium(R) D CPU 2.80GHz
CPU vendor:	GenuineIntel
CPU family:	15
CPU model:	6
CPU stepping:	2
CPU cache:	2048 KB
CPU frequency:	2794.468

PCI devices

The following table shows all PCI devices that were plugged in the testmachine during the testrun.

category	name
SMBus	Intel Corp.
Ethernet controller	Marvell Technology Group Ltd.
VGA compatible controller	Intel Corp.
IDE interface	Intel Corp.
0403	Intel Corp.
ISA bridge	Intel Corp.
PCI bridge	Intel Corp. 82801 PCI Bridge (rev e1)
USB Controller	Intel Corp.
PCI bridge	Intel Corp.
Host bridge	Intel Corp.
FireWire (IEEE 1394)	Texas Instruments TSB43AB23 IEEE-1394a-2000 Controller (PHY/Link)

Testresults

BYTE nbench benchmark

The following results were acquired using the Linux port of release 2 of BYTE Magazine's BYTEmark benchmark program.

RTAI testsuite

UP scheduler - latency

The difference in time between the expected switch time and the time when a task is actually called by the scheduler is measured. For this test the RTAI UP scheduler is used.

LXRT scheduler - latency

The difference in time between the expected switch time and the time when a task is actually called by the scheduler is measured. For this test the RTAI LXRT scheduler is used.

UP scheduler - preemption

The following table shows the results of a stress test aimed at verifying that the schedulers preempt well under intense load. It is a simple test that combines the latency calibration task with a fast and slow task in such a way to have two levels of preemption, nesting on an odd number of tasks. It shows the maximum jitter of the fast task, which has the second highest priority, and of the slow which has the lowest priority. Reasonable jitters are a clear indication of preemption.

LXRT scheduler - preemption

The following table shows the results of a stress test aimed at verifying that the schedulers preempt well under intense load. It is a simple test that combines the latency calibration task with a fast and slow task in such a way to have two levels of preemption, nesting on an odd number of tasks. It shows the maximum jitter of the fast task, which has the second highest priority, and of the slow which has the lowest priority. Reasonable jitters are a clear indication of preemption.