OpenCores
URL https://opencores.org/ocsvn/openrisc/openrisc/trunk

Subversion Repositories openrisc

[/] [openrisc/] [trunk/] [rtos/] [ecos-2.0/] [doc/] [html/] [ref/] [kernel-characterization.html] - Blame information for rev 588

Go to most recent revision | Details | Compare with Previous | View Log

Line No. Rev Author Line
1 28 unneback
<!-- Copyright (C) 2003 Red Hat, Inc.                                -->
2
<!-- This material may be distributed only subject to the terms      -->
3
<!-- and conditions set forth in the Open Publication License, v1.0  -->
4
<!-- or later (the latest version is presently available at          -->
5
<!-- http://www.opencontent.org/openpub/).                           -->
6
<!-- Distribution of the work or derivative of the work in any       -->
7
<!-- standard (paper) book form is prohibited unless prior           -->
8
<!-- permission is obtained from the copyright holder.               -->
9
<HTML
10
><HEAD
11
><TITLE
12
>Kernel Real-time Characterization</TITLE
13
><meta name="MSSmartTagsPreventParsing" content="TRUE">
14
<META
15
NAME="GENERATOR"
16
CONTENT="Modular DocBook HTML Stylesheet Version 1.76b+
17
"><LINK
18
REL="HOME"
19
TITLE="eCos Reference Manual"
20
HREF="ecos-ref.html"><LINK
21
REL="UP"
22
TITLE="The eCos Kernel"
23
HREF="kernel.html"><LINK
24
REL="PREVIOUS"
25
TITLE="Interrupt Handling"
26
HREF="kernel-interrupts.html"><LINK
27
REL="NEXT"
28
TITLE="RedBoot&#8482; User's Guide"
29
HREF="redboot.html"></HEAD
30
><BODY
31
CLASS="REFENTRY"
32
BGCOLOR="#FFFFFF"
33
TEXT="#000000"
34
LINK="#0000FF"
35
VLINK="#840084"
36
ALINK="#0000FF"
37
><DIV
38
CLASS="NAVHEADER"
39
><TABLE
40
SUMMARY="Header navigation table"
41
WIDTH="100%"
42
BORDER="0"
43
CELLPADDING="0"
44
CELLSPACING="0"
45
><TR
46
><TH
47
COLSPAN="3"
48
ALIGN="center"
49
>eCos Reference Manual</TH
50
></TR
51
><TR
52
><TD
53
WIDTH="10%"
54
ALIGN="left"
55
VALIGN="bottom"
56
><A
57
HREF="kernel-interrupts.html"
58
ACCESSKEY="P"
59
>Prev</A
60
></TD
61
><TD
62
WIDTH="80%"
63
ALIGN="center"
64
VALIGN="bottom"
65
></TD
66
><TD
67
WIDTH="10%"
68
ALIGN="right"
69
VALIGN="bottom"
70
><A
71
HREF="redboot.html"
72
ACCESSKEY="N"
73
>Next</A
74
></TD
75
></TR
76
></TABLE
77
><HR
78
ALIGN="LEFT"
79
WIDTH="100%"></DIV
80
><H1
81
><A
82
NAME="KERNEL-CHARACTERIZATION">Kernel Real-time Characterization</H1
83
><DIV
84
CLASS="REFNAMEDIV"
85
><A
86
NAME="AEN2068"
87
></A
88
><H2
89
>Name</H2
90
>tm_basic&nbsp;--&nbsp;Measure the performance of the eCos kernel</DIV
91
><DIV
92
CLASS="REFSECT1"
93
><A
94
NAME="KERNEL-CHARACTERIZATION-DESCRIPTION"
95
></A
96
><H2
97
>Description</H2
98
><P
99
>When building a real-time system, care must be taken to ensure that
100
the system will be able to perform properly within the constraints of
101
that system. One of these constraints may be how fast certain
102
operations can be performed. Another might be how deterministic the
103
overall behavior of the system is. Lastly the memory footprint (size)
104
and unit cost may be important.
105
        </P
106
><P
107
>One of the major problems encountered while evaluating a system will
108
be how to compare it with possible alternatives. Most manufacturers of
109
real-time systems publish performance numbers, ostensibly so that
110
users can compare the different offerings. However, what these numbers
111
mean and how they were gathered is often not clear. The values are
112
typically measured on a particular piece of hardware, so in order to
113
truly compare, one must obtain measurements for exactly the same set
114
of hardware that were gathered in a similar fashion.
115
        </P
116
><P
117
>Two major items need to be present in any given set of measurements.
118
First, the raw values for the various operations; these are typically
119
quite easy to measure and will be available for most systems. Second,
120
the determinacy of the numbers; in other words how much the value
121
might change depending on other factors within the system. This value
122
is affected by a number of factors: how long interrupts might be
123
masked, whether or not the function can be interrupted, even very
124
hardware-specific effects such as cache locality and pipeline usage.
125
It is very difficult to measure the determinacy of any given
126
operation, but that determinacy is fundamentally important to proper
127
overall characterization of a system.
128
        </P
129
><P
130
>In the discussion and numbers that follow, three key measurements are
131
provided. The first measurement is an estimate of the interrupt
132
latency: this is the length of time from when a hardware interrupt
133
occurs until its Interrupt Service Routine (ISR) is called. The second
134
measurement is an estimate of overall interrupt overhead: this is the
135
length of time average interrupt processing takes, as measured by the
136
real-time clock interrupt (other interrupt sources will certainly take
137
a different amount of time, but this data cannot be easily gathered).
138
The third measurement consists of the timings for the various kernel
139
primitives.
140
          </P
141
></DIV
142
><DIV
143
CLASS="REFSECT1"
144
><A
145
NAME="KERNEL-CHARACTERIZATION-METHODOLOGY"
146
></A
147
><H2
148
>Methodology</H2
149
><P
150
>Key operations in the kernel were measured by using a simple test
151
program which exercises the various kernel primitive operations. A
152
hardware timer, normally the one used to drive the real-time clock,
153
was used for these measurements. In most cases this timer can be read
154
with quite high resolution, typically in the range of a few
155
microseconds. For each measurement, the operation was repeated a
156
number of times. Time stamps were obtained directly before and after
157
the operation was performed. The data gathered for the entire set of
158
operations was then analyzed, generating average (mean), maximum and
159
minimum values. The sample variance (a measure of how close most
160
samples are to the mean) was also calculated. The cost of obtaining
161
the real-time clock timer values was also measured, and was subtracted
162
from all other times.
163
          </P
164
><P
165
>Most kernel functions can be measured separately. In each case, a
166
reasonable number of iterations are performed. Where the test case
167
involves a kernel object, for example creating a task, each iteration
168
is performed on a different object. There is also a set of tests which
169
measures the interactions between multiple tasks and certain kernel
170
primitives. Most functions are tested in such a way as to determine
171
the variations introduced by varying numbers of objects in the system.
172
For example, the mailbox tests measure the cost of a 'peek' operation
173
when the mailbox is empty, has a single item, and has multiple items
174
present. In this way, any effects of the state of the object or how
175
many items it contains can be determined.
176
          </P
177
><P
178
>There are a few things to consider about these measurements. Firstly,
179
they are quite micro in scale and only measure the operation in
180
question. These measurements do not adequately describe how the
181
timings would be perturbed in a real system with multiple interrupting
182
sources. Secondly, the possible aberration incurred by the real-time
183
clock (system heartbeat tick) is explicitly avoided. Virtually all
184
kernel functions have been designed to be interruptible. Thus the
185
times presented are typical, but best case, since any particular
186
function may be interrupted by the clock tick processing. This number
187
is explicitly calculated so that the value may be included in any
188
deadline calculations required by the end user. Lastly, the reported
189
measurements were obtained from a system built with all options at
190
their default values. Kernel instrumentation and asserts are also
191
disabled for these measurements. Any number of configuration options
192
can change the measured results, sometimes quite dramatically. For
193
example, mutexes are using priority inheritance in these measurements.
194
The numbers will change if the system is built with priority
195
inheritance on mutex variables turned off.
196
          </P
197
><P
198
>The final value that is measured is an estimate of interrupt latency.
199
This particular value is not explicitly calculated in the test program
200
used, but rather by instrumenting the kernel itself. The raw number of
201
timer ticks that elapse between the time the timer generates an
202
interrupt and the start of the timer ISR is kept in the kernel. These
203
values are printed by the test program after all other operations have
204
been tested. Thus this should be a reasonable estimate of the
205
interrupt latency over time.
206
          </P
207
></DIV
208
><DIV
209
CLASS="REFSECT1"
210
><A
211
NAME="KERNEL-CHARACTERIZATION-USING-MEASUREMENTS"
212
></A
213
><H2
214
>Using these Measurements</H2
215
><P
216
>These measurements can be used in a number of ways. The most typical
217
use will be to compare different real-time kernel offerings on similar
218
hardware, another will be to estimate the cost of implementing a task
219
using eCos (applications can be examined to see what effect the kernel
220
operations will have on the total execution time). Another use would
221
be to observe how the tuning of the kernel affects overall operation.
222
          </P
223
></DIV
224
><DIV
225
CLASS="REFSECT1"
226
><A
227
NAME="KERNEL-CHARACTERIZATION-INFLUENCES"
228
></A
229
><H2
230
>Influences on Performance</H2
231
><P
232
>A number of factors can affect real-time performance in a system. One
233
of the most common factors, yet most difficult to characterize, is the
234
effect of device drivers and interrupts on system timings. Different
235
device drivers will have differing requirements as to how long
236
interrupts are suppressed, for example. The eCos system has been
237
designed with this in mind, by separating the management of interrupts
238
(ISR handlers) and the processing required by the interrupt
239
(DSR&#8212;Deferred Service Routine&#8212; handlers). However, since
240
there is so much variability here, and indeed most device drivers will
241
come from the end users themselves, these effects cannot be reliably
242
measured. Attempts have been made to measure the overhead of the
243
single interrupt that eCos relies on, the real-time clock timer. This
244
should give you a reasonable idea of the cost of executing interrupt
245
handling for devices.
246
          </P
247
></DIV
248
><DIV
249
CLASS="REFSECT1"
250
><A
251
NAME="KERNEL-CHARACTERIZATION-MEASURED-ITEMS"
252
></A
253
><H2
254
>Measured Items</H2
255
><P
256
>This section describes the various tests and the numbers presented.
257
All tests use the C kernel API (available by way of
258
<TT
259
CLASS="FILENAME"
260
>cyg/kernel/kapi.h</TT
261
>). There is a single main thread
262
in the system that performs the various tests. Additional threads may
263
be created as part of the testing, but these are short lived and are
264
destroyed between tests unless otherwise noted. The terminology
265
&#8220;lower priority&#8221; means a priority that is less important,
266
not necessarily lower in numerical value. A higher priority thread
267
will run in preference to a lower priority thread even though the
268
priority value of the higher priority thread may be numerically less
269
than that of the lower priority thread.
270
          </P
271
><DIV
272
CLASS="REFSECT2"
273
><A
274
NAME="KERNEL-CHARACTERIZATION-MEASURE-THREADS"
275
></A
276
><H3
277
>Thread Primitives</H3
278
><P
279
></P
280
><DIV
281
CLASS="VARIABLELIST"
282
><DL
283
><DT
284
>Create thread</DT
285
><DD
286
><P
287
>This test measures the <TT
288
CLASS="FUNCTION"
289
>cyg_thread_create()</TT
290
> call.
291
Each call creates a totally new thread. The set of threads created by
292
this test will be reused in the subsequent thread primitive tests.
293
                </P
294
></DD
295
><DT
296
>Yield thread</DT
297
><DD
298
><P
299
>This test measures the <TT
300
CLASS="FUNCTION"
301
>cyg_thread_yield()</TT
302
> call.
303
For this test, there are no other runnable threads, thus the test
304
should just measure the overhead of trying to give up the CPU.
305
                </P
306
></DD
307
><DT
308
>Suspend &#0091;suspended&#0093; thread</DT
309
><DD
310
><P
311
>This test measures the <TT
312
CLASS="FUNCTION"
313
>cyg_thread_suspend()</TT
314
> call.
315
A thread may be suspended multiple times; each thread is already
316
suspended from its initial creation, and is suspended again.
317
                </P
318
></DD
319
><DT
320
>Resume thread</DT
321
><DD
322
><P
323
>This test measures the <TT
324
CLASS="FUNCTION"
325
>cyg_thread_resume()</TT
326
> call.
327
All of the threads have a suspend count of 2, thus this call does not
328
make them runnable. This test just measures the overhead of resuming a
329
thread.
330
                </P
331
></DD
332
><DT
333
>Set priority</DT
334
><DD
335
><P
336
>This test measures the <TT
337
CLASS="FUNCTION"
338
>cyg_thread_set_priority()</TT
339
>
340
call. Each thread, currently suspended, has its priority set to a new
341
value.
342
                </P
343
></DD
344
><DT
345
>Get priority</DT
346
><DD
347
><P
348
>This test measures the <TT
349
CLASS="FUNCTION"
350
>cyg_thread_get_priority()</TT
351
>
352
call.
353
                </P
354
></DD
355
><DT
356
>Kill &#0091;suspended&#0093; thread</DT
357
><DD
358
><P
359
>This test measures the <TT
360
CLASS="FUNCTION"
361
>cyg_thread_kill()</TT
362
> call.
363
Each thread in the set is killed. All threads are known to be
364
suspended before being killed.
365
                </P
366
></DD
367
><DT
368
>Yield &#0091;no other&#0093; thread</DT
369
><DD
370
><P
371
>This test measures the <TT
372
CLASS="FUNCTION"
373
>cyg_thread_yield()</TT
374
> call
375
again. This is to demonstrate that the
376
<TT
377
CLASS="FUNCTION"
378
>cyg_thread_yield()</TT
379
> call has a fixed overhead,
380
regardless of whether there are other threads in the system.
381
                </P
382
></DD
383
><DT
384
>Resume &#0091;suspended low priority&#0093; thread</DT
385
><DD
386
><P
387
>This test measures the <TT
388
CLASS="FUNCTION"
389
>cyg_thread_resume()</TT
390
> call
391
again. In this case, the thread being resumed is lower priority than
392
the main thread, thus it will simply become ready to run but not be
393
granted the CPU. This test measures the cost of making a thread ready
394
to run.
395
                </P
396
></DD
397
><DT
398
>Resume &#0091;runnable low priority&#0093; thread</DT
399
><DD
400
><P
401
>This test measures the <TT
402
CLASS="FUNCTION"
403
>cyg_thread_resume()</TT
404
> call
405
again. In this case, the thread being resumed is lower priority than
406
the main thread and has already been made runnable, so in fact the
407
resume call has no effect.
408
                </P
409
></DD
410
><DT
411
>Suspend &#0091;runnable&#0093; thread</DT
412
><DD
413
><P
414
>This test measures the <TT
415
CLASS="FUNCTION"
416
>cyg_thread_suspend()</TT
417
> call
418
again. In this case, each thread has already been made runnable (by
419
previous tests).
420
                </P
421
></DD
422
><DT
423
>Yield &#0091;only low priority&#0093; thread</DT
424
><DD
425
><P
426
>This test measures the <TT
427
CLASS="FUNCTION"
428
>cyg_thread_yield()</TT
429
> call.
430
In this case, there are many other runnable threads, but they are all
431
lower priority than the main thread, thus no thread switches will take
432
place.
433
                </P
434
></DD
435
><DT
436
>Suspend &#0091;runnable-&gt;not runnable&#0093; thread</DT
437
><DD
438
><P
439
>This test measures the <TT
440
CLASS="FUNCTION"
441
>cyg_thread_suspend()</TT
442
> call
443
again. The thread being suspended will become non-runnable by this
444
action.
445
                </P
446
></DD
447
><DT
448
>Kill &#0091;runnable&#0093; thread</DT
449
><DD
450
><P
451
>This test measures the <TT
452
CLASS="FUNCTION"
453
>cyg_thread_kill()</TT
454
> call
455
again. In this case, the thread being killed is currently runnable,
456
but lower priority than the main thread.
457
                </P
458
></DD
459
><DT
460
>Resume &#0091;high priority&#0093; thread</DT
461
><DD
462
><P
463
>This test measures the <TT
464
CLASS="FUNCTION"
465
>cyg_thread_resume()</TT
466
> call.
467
The thread being resumed is higher priority than the main thread, thus
468
a thread switch will take place on each call. In fact there will be
469
two thread switches; one to the new higher priority thread and a
470
second back to the test thread. The test thread exits immediately.
471
                </P
472
></DD
473
><DT
474
>Thread switch</DT
475
><DD
476
><P
477
>This test attempts to measure the cost of switching from one thread to
478
another. Two equal priority threads are started and they will each
479
yield to the other for a number of iterations. A time stamp is
480
gathered in one thread before the
481
<TT
482
CLASS="FUNCTION"
483
>cyg_thread_yield()</TT
484
> call and after the call in the
485
other thread.
486
                </P
487
></DD
488
></DL
489
></DIV
490
></DIV
491
><DIV
492
CLASS="REFSECT2"
493
><A
494
NAME="KERNEL-CHARACTERIZATION-MEASURE-SCHEDULER"
495
></A
496
><H3
497
>Scheduler Primitives</H3
498
><P
499
></P
500
><DIV
501
CLASS="VARIABLELIST"
502
><DL
503
><DT
504
>Scheduler lock</DT
505
><DD
506
><P
507
>This test measures the <TT
508
CLASS="FUNCTION"
509
>cyg_scheduler_lock()</TT
510
> call.
511
                </P
512
></DD
513
><DT
514
>Scheduler unlock &#0091;0 threads&#0093;</DT
515
><DD
516
><P
517
>This test measures the <TT
518
CLASS="FUNCTION"
519
>cyg_scheduler_unlock()</TT
520
>
521
call. There are no other threads in the system and the unlock happens
522
immediately after a lock so there will be no pending DSR&#8217;s to
523
run.
524
                </P
525
></DD
526
><DT
527
>Scheduler unlock &#0091;1 suspended thread&#0093;</DT
528
><DD
529
><P
530
>This test measures the <TT
531
CLASS="FUNCTION"
532
>cyg_scheduler_unlock()</TT
533
>
534
call. There is one other thread in the system which is currently
535
suspended.
536
                </P
537
></DD
538
><DT
539
>Scheduler unlock &#0091;many suspended threads&#0093;</DT
540
><DD
541
><P
542
>This test measures the <TT
543
CLASS="FUNCTION"
544
>cyg_scheduler_unlock()</TT
545
>
546
call. There are many other threads in the system which are currently
547
suspended. The purpose of this test is to determine the cost of having
548
additional threads in the system when the scheduler is activated by
549
way of <TT
550
CLASS="FUNCTION"
551
>cyg_scheduler_unlock()</TT
552
>.
553
                </P
554
></DD
555
><DT
556
>Scheduler unlock &#0091;many low priority threads&#0093;</DT
557
><DD
558
><P
559
>This test measures the <TT
560
CLASS="FUNCTION"
561
>cyg_scheduler_unlock()</TT
562
>
563
call. There are many other threads in the system which are runnable
564
but are lower priority than the main thread. The purpose of this test
565
is to determine the cost of having additional threads in the system
566
when the scheduler is activated by way of
567
<TT
568
CLASS="FUNCTION"
569
>cyg_scheduler_unlock()</TT
570
>.
571
                </P
572
></DD
573
></DL
574
></DIV
575
></DIV
576
><DIV
577
CLASS="REFSECT2"
578
><A
579
NAME="KERNEL-CHARACTERIZATION-MEASURE-MUTEX"
580
></A
581
><H3
582
>Mutex Primitives</H3
583
><P
584
></P
585
><DIV
586
CLASS="VARIABLELIST"
587
><DL
588
><DT
589
>Init mutex</DT
590
><DD
591
><P
592
>This test measures the <TT
593
CLASS="FUNCTION"
594
>cyg_mutex_init()</TT
595
> call. A
596
number of separate mutex variables are created. The purpose of this
597
test is to measure the cost of creating a new mutex and introducing it
598
to the system.
599
                </P
600
></DD
601
><DT
602
>Lock &#0091;unlocked&#0093; mutex</DT
603
><DD
604
><P
605
>This test measures the <TT
606
CLASS="FUNCTION"
607
>cyg_mutex_lock()</TT
608
> call. The
609
purpose of this test is to measure the cost of locking a mutex which
610
is currently unlocked. There are no other threads executing in the
611
system while this test runs.
612
                </P
613
></DD
614
><DT
615
>Unlock &#0091;locked&#0093; mutex</DT
616
><DD
617
><P
618
>This test measures the <TT
619
CLASS="FUNCTION"
620
>cyg_mutex_unlock()</TT
621
> call.
622
The purpose of this test is to measure the cost of unlocking a mutex
623
which is currently locked. There are no other threads executing in the
624
system while this test runs.
625
                </P
626
></DD
627
><DT
628
>Trylock &#0091;unlocked&#0093; mutex</DT
629
><DD
630
><P
631
>This test measures the <TT
632
CLASS="FUNCTION"
633
>cyg_mutex_trylock()</TT
634
> call.
635
The purpose of this test is to measure the cost of locking a mutex
636
which is currently unlocked. There are no other threads executing in
637
the system while this test runs.
638
                </P
639
></DD
640
><DT
641
>Trylock &#0091;locked&#0093; mutex</DT
642
><DD
643
><P
644
>This test measures the <TT
645
CLASS="FUNCTION"
646
>cyg_mutex_trylock()</TT
647
> call.
648
The purpose of this test is to measure the cost of locking a mutex
649
which is currently locked. There are no other threads executing in the
650
system while this test runs.
651
                </P
652
></DD
653
><DT
654
>Destroy mutex</DT
655
><DD
656
><P
657
>This test measures the <TT
658
CLASS="FUNCTION"
659
>cyg_mutex_destroy()</TT
660
> call.
661
The purpose of this test is to measure the cost of deleting a mutex
662
from the system. There are no other threads executing in the system
663
while this test runs.
664
                </P
665
></DD
666
><DT
667
>Unlock/Lock mutex</DT
668
><DD
669
><P
670
>This test attempts to measure the cost of unlocking a mutex for which
671
there is another higher priority thread waiting. When the mutex is
672
unlocked, the higher priority waiting thread will immediately take the
673
lock. The time from when the unlock is issued until after the lock
674
succeeds in the second thread is measured, thus giving the round-trip
675
or circuit time for this type of synchronizer.
676
                </P
677
></DD
678
></DL
679
></DIV
680
></DIV
681
><DIV
682
CLASS="REFSECT2"
683
><A
684
NAME="KERNEL-CHARACTERIZATION-MEASURE-MAILBOX"
685
></A
686
><H3
687
>Mailbox Primitives</H3
688
><P
689
></P
690
><DIV
691
CLASS="VARIABLELIST"
692
><DL
693
><DT
694
>Create mbox</DT
695
><DD
696
><P
697
>This test measures the <TT
698
CLASS="FUNCTION"
699
>cyg_mbox_create()</TT
700
> call. A
701
number of separate mailboxes is created. The purpose of this test is
702
to measure the cost of creating a new mailbox and introducing it to
703
the system.
704
                </P
705
></DD
706
><DT
707
>Peek &#0091;empty&#0093; mbox</DT
708
><DD
709
><P
710
>This test measures the <TT
711
CLASS="FUNCTION"
712
>cyg_mbox_peek()</TT
713
> call. An
714
attempt is made to peek the value in each mailbox, which is currently
715
empty. The purpose of this test is to measure the cost of checking a
716
mailbox for a value without blocking.
717
                </P
718
></DD
719
><DT
720
>Put &#0091;first&#0093; mbox</DT
721
><DD
722
><P
723
>This test measures the <TT
724
CLASS="FUNCTION"
725
>cyg_mbox_put()</TT
726
> call. One
727
item is added to a currently empty mailbox. The purpose of this test
728
is to measure the cost of adding an item to a mailbox. There are no
729
other threads currently waiting for mailbox items to arrive.
730
                </P
731
></DD
732
><DT
733
>Peek &#0091;1 msg&#0093; mbox</DT
734
><DD
735
><P
736
>This test measures the <TT
737
CLASS="FUNCTION"
738
>cyg_mbox_peek()</TT
739
> call. An
740
attempt is made to peek the value in each mailbox, which contains a
741
single item. The purpose of this test is to measure the cost of
742
checking a mailbox which has data to deliver.
743
                </P
744
></DD
745
><DT
746
>Put &#0091;second&#0093; mbox</DT
747
><DD
748
><P
749
>This test measures the <TT
750
CLASS="FUNCTION"
751
>cyg_mbox_put()</TT
752
> call. A
753
second item is added to a mailbox. The purpose of this test is to
754
measure the cost of adding an additional item to a mailbox. There are
755
no other threads currently waiting for mailbox items to arrive.
756
                </P
757
></DD
758
><DT
759
>Peek &#0091;2 msgs&#0093; mbox</DT
760
><DD
761
><P
762
>This test measures the <TT
763
CLASS="FUNCTION"
764
>cyg_mbox_peek()</TT
765
> call. An
766
attempt is made to peek the value in each mailbox, which contains two
767
items. The purpose of this test is to measure the cost of checking a
768
mailbox which has data to deliver.
769
                </P
770
></DD
771
><DT
772
>Get &#0091;first&#0093; mbox</DT
773
><DD
774
><P
775
>This test measures the <TT
776
CLASS="FUNCTION"
777
>cyg_mbox_get()</TT
778
> call. The
779
first item is removed from a mailbox that currently contains two
780
items. The purpose of this test is to measure the cost of obtaining an
781
item from a mailbox without blocking.
782
              </P
783
></DD
784
><DT
785
>Get &#0091;second&#0093; mbox</DT
786
><DD
787
><P
788
>This test measures the <TT
789
CLASS="FUNCTION"
790
>cyg_mbox_get()</TT
791
> call. The
792
last item is removed from a mailbox that currently contains one item.
793
The purpose of this test is to measure the cost of obtaining an item
794
from a mailbox without blocking.
795
                </P
796
></DD
797
><DT
798
>Tryput &#0091;first&#0093; mbox</DT
799
><DD
800
><P
801
>This test measures the <TT
802
CLASS="FUNCTION"
803
>cyg_mbox_tryput()</TT
804
> call. A
805
single item is added to a currently empty mailbox. The purpose of this
806
test is to measure the cost of adding an item to a mailbox.
807
                </P
808
></DD
809
><DT
810
>Peek item &#0091;non-empty&#0093; mbox</DT
811
><DD
812
><P
813
>This test measures the <TT
814
CLASS="FUNCTION"
815
>cyg_mbox_peek_item()</TT
816
> call.
817
A single item is fetched from a mailbox that contains a single item.
818
The purpose of this test is to measure the cost of obtaining an item
819
without disturbing the mailbox.
820
                </P
821
></DD
822
><DT
823
>Tryget &#0091;non-empty&#0093; mbox</DT
824
><DD
825
><P
826
>This test measures the <TT
827
CLASS="FUNCTION"
828
>cyg_mbox_tryget()</TT
829
> call. A
830
single item is removed from a mailbox that contains exactly one item.
831
The purpose of this test is to measure the cost of obtaining one item
832
from a non-empty mailbox.
833
                </P
834
></DD
835
><DT
836
>Peek item &#0091;empty&#0093; mbox</DT
837
><DD
838
><P
839
>This test measures the <TT
840
CLASS="FUNCTION"
841
>cyg_mbox_peek_item()</TT
842
> call.
843
An attempt is made to fetch an item from a mailbox that is empty. The
844
purpose of this test is to measure the cost of trying to obtain an
845
item when the mailbox is empty.
846
                </P
847
></DD
848
><DT
849
>Tryget &#0091;empty&#0093; mbox</DT
850
><DD
851
><P
852
>This test measures the <TT
853
CLASS="FUNCTION"
854
>cyg_mbox_tryget()</TT
855
> call. An
856
attempt is made to fetch an item from a mailbox that is empty. The
857
purpose of this test is to measure the cost of trying to obtain an
858
item when the mailbox is empty.
859
                </P
860
></DD
861
><DT
862
>Waiting to get mbox</DT
863
><DD
864
><P
865
>This test measures the <TT
866
CLASS="FUNCTION"
867
>cyg_mbox_waiting_to_get()</TT
868
>
869
call. The purpose of this test is to measure the cost of determining
870
how many threads are waiting to obtain a message from this mailbox.
871
                </P
872
></DD
873
><DT
874
>Waiting to put mbox</DT
875
><DD
876
><P
877
>This test measures the <TT
878
CLASS="FUNCTION"
879
>cyg_mbox_waiting_to_put()</TT
880
>
881
call. The purpose of this test is to measure the cost of determining
882
how many threads are waiting to put a message into this mailbox.
883
                </P
884
></DD
885
><DT
886
>Delete mbox</DT
887
><DD
888
><P
889
>This test measures the <TT
890
CLASS="FUNCTION"
891
>cyg_mbox_delete()</TT
892
> call.
893
The purpose of this test is to measure the cost of destroying a
894
mailbox and removing it from the system.
895
                </P
896
></DD
897
><DT
898
>Put/Get mbox</DT
899
><DD
900
><P
901
>In this round-trip test, one thread is sending data to a mailbox that
902
is being consumed by another thread. The time from when the data is
903
put into the mailbox until it has been delivered to the waiting thread
904
is measured. Note that this time will contain a thread switch.
905
                </P
906
></DD
907
></DL
908
></DIV
909
></DIV
910
><DIV
911
CLASS="REFSECT2"
912
><A
913
NAME="KERNEL-CHARACTERIZATION-MEASURE-SEMAPHORE"
914
></A
915
><H3
916
>Semaphore Primitives</H3
917
><P
918
></P
919
><DIV
920
CLASS="VARIABLELIST"
921
><DL
922
><DT
923
>Init semaphore</DT
924
><DD
925
><P
926
>This test measures the <TT
927
CLASS="FUNCTION"
928
>cyg_semaphore_init()</TT
929
> call.
930
A number of separate semaphore objects are created and introduced to
931
the system. The purpose of this test is to measure the cost of
932
creating a new semaphore.
933
                </P
934
></DD
935
><DT
936
>Post &#0091;0&#0093; semaphore</DT
937
><DD
938
><P
939
>This test measures the <TT
940
CLASS="FUNCTION"
941
>cyg_semaphore_post()</TT
942
> call.
943
Each semaphore currently has a value of 0 and there are no other
944
threads in the system. The purpose of this test is to measure the
945
overhead cost of posting to a semaphore. This cost will differ if
946
there is a thread waiting for the semaphore.
947
                </P
948
></DD
949
><DT
950
>Wait &#0091;1&#0093; semaphore</DT
951
><DD
952
><P
953
>This test measures the <TT
954
CLASS="FUNCTION"
955
>cyg_semaphore_wait()</TT
956
> call.
957
The semaphore has a current value of 1 so the call is non-blocking.
958
The purpose of the test is to measure the overhead of
959
&#8220;taking&#8221; a semaphore.
960
                </P
961
></DD
962
><DT
963
>Trywait &#0091;0&#0093; semaphore</DT
964
><DD
965
><P
966
>This test measures the <TT
967
CLASS="FUNCTION"
968
>cyg_semaphore_trywait()</TT
969
>
970
call. The semaphore has a value of 0 when the call is made. The
971
purpose of this test is to measure the cost of seeing if a semaphore
972
can be &#8220;taken&#8221; without blocking. In this case, the answer
973
would be no.
974
                </P
975
></DD
976
><DT
977
>Trywait &#0091;1&#0093; semaphore</DT
978
><DD
979
><P
980
>This test measures the <TT
981
CLASS="FUNCTION"
982
>cyg_semaphore_trywait()</TT
983
>
984
call. The semaphore has a value of 1 when the call is made. The
985
purpose of this test is to measure the cost of seeing if a semaphore
986
can be &#8220;taken&#8221; without blocking. In this case, the answer
987
would be yes.
988
                </P
989
></DD
990
><DT
991
>Peek semaphore</DT
992
><DD
993
><P
994
>This test measures the <TT
995
CLASS="FUNCTION"
996
>cyg_semaphore_peek()</TT
997
> call.
998
The purpose of this test is to measure the cost of obtaining the
999
current semaphore count value.
1000
                </P
1001
></DD
1002
><DT
1003
>Destroy semaphore</DT
1004
><DD
1005
><P
1006
>This test measures the <TT
1007
CLASS="FUNCTION"
1008
>cyg_semaphore_destroy()</TT
1009
>
1010
call. The purpose of this test is to measure the cost of deleting a
1011
semaphore from the system.
1012
                </P
1013
></DD
1014
><DT
1015
>Post/Wait semaphore</DT
1016
><DD
1017
><P
1018
>In this round-trip test, two threads are passing control back and
1019
forth by using a semaphore. The time from when one thread calls
1020
<TT
1021
CLASS="FUNCTION"
1022
>cyg_semaphore_post()</TT
1023
> until the other thread
1024
completes its <TT
1025
CLASS="FUNCTION"
1026
>cyg_semaphore_wait()</TT
1027
> is measured.
1028
Note that each iteration of this test will involve a thread switch.
1029
                </P
1030
></DD
1031
></DL
1032
></DIV
1033
></DIV
1034
><DIV
1035
CLASS="REFSECT2"
1036
><A
1037
NAME="KERNEL-CHARACTERIZATION-MEASURE-COUNTERS"
1038
></A
1039
><H3
1040
>Counters</H3
1041
><P
1042
></P
1043
><DIV
1044
CLASS="VARIABLELIST"
1045
><DL
1046
><DT
1047
>Create counter</DT
1048
><DD
1049
><P
1050
>This test measures the <TT
1051
CLASS="FUNCTION"
1052
>cyg_counter_create()</TT
1053
> call.
1054
A number of separate counters are created. The purpose of this test is
1055
to measure the cost of creating a new counter and introducing it to
1056
the system.
1057
                </P
1058
></DD
1059
><DT
1060
>Get counter value</DT
1061
><DD
1062
><P
1063
>This test measures the
1064
<TT
1065
CLASS="FUNCTION"
1066
>cyg_counter_current_value()</TT
1067
> call. The current
1068
value of each counter is obtained.
1069
                </P
1070
></DD
1071
><DT
1072
>Set counter value</DT
1073
><DD
1074
><P
1075
>This test measures the <TT
1076
CLASS="FUNCTION"
1077
>cyg_counter_set_value()</TT
1078
>
1079
call. Each counter is set to a new value.
1080
                </P
1081
></DD
1082
><DT
1083
>Tick counter</DT
1084
><DD
1085
><P
1086
>This test measures the <TT
1087
CLASS="FUNCTION"
1088
>cyg_counter_tick()</TT
1089
> call.
1090
Each counter is &#8220;ticked&#8221; once.
1091
                </P
1092
></DD
1093
><DT
1094
>Delete counter</DT
1095
><DD
1096
><P
1097
>This test measures the <TT
1098
CLASS="FUNCTION"
1099
>cyg_counter_delete()</TT
1100
> call.
1101
Each counter is deleted from the system. The purpose of this test is
1102
to measure the cost of deleting a counter object.
1103
                </P
1104
></DD
1105
></DL
1106
></DIV
1107
></DIV
1108
><DIV
1109
CLASS="REFSECT2"
1110
><A
1111
NAME="KERNEL-CHARACTERIZATION-MEASURE-ALARMS"
1112
></A
1113
><H3
1114
>Alarms</H3
1115
><P
1116
></P
1117
><DIV
1118
CLASS="VARIABLELIST"
1119
><DL
1120
><DT
1121
>Create alarm</DT
1122
><DD
1123
><P
1124
>This test measures the <TT
1125
CLASS="FUNCTION"
1126
>cyg_alarm_create()</TT
1127
> call. A
1128
number of separate alarms are created, all attached to the same
1129
counter object. The purpose of this test is to measure the cost of
1130
creating a new counter and introducing it to the system.
1131
                </P
1132
></DD
1133
><DT
1134
>Initialize alarm</DT
1135
><DD
1136
><P
1137
>This test measures the <TT
1138
CLASS="FUNCTION"
1139
>cyg_alarm_initialize()</TT
1140
>
1141
call. Each alarm is initialized to a small value.
1142
                </P
1143
></DD
1144
><DT
1145
>Disable alarm</DT
1146
><DD
1147
><P
1148
>This test measures the <TT
1149
CLASS="FUNCTION"
1150
>cyg_alarm_disable()</TT
1151
> call.
1152
Each alarm is explicitly disabled.
1153
                </P
1154
></DD
1155
><DT
1156
>Enable alarm</DT
1157
><DD
1158
><P
1159
>This test measures the <TT
1160
CLASS="FUNCTION"
1161
>cyg_alarm_enable()</TT
1162
> call.
1163
Each alarm is explicitly enabled.
1164
                </P
1165
></DD
1166
><DT
1167
>Delete alarm</DT
1168
><DD
1169
><P
1170
>This test measures the <TT
1171
CLASS="FUNCTION"
1172
>cyg_alarm_delete()</TT
1173
> call.
1174
Each alarm is destroyed. The purpose of this test is to measure the
1175
cost of deleting an alarm and removing it from the system.
1176
                </P
1177
></DD
1178
><DT
1179
>Tick counter &#0091;1 alarm&#0093;</DT
1180
><DD
1181
><P
1182
>This test measures the <TT
1183
CLASS="FUNCTION"
1184
>cyg_counter_tick()</TT
1185
> call. A
1186
counter is created that has a single alarm attached to it. The purpose
1187
of this test is to measure the cost of &#8220;ticking&#8221; a counter
1188
when it has a single attached alarm. In this test, the alarm is not
1189
activated (fired).
1190
                </P
1191
></DD
1192
><DT
1193
>Tick counter &#0091;many alarms&#0093;</DT
1194
><DD
1195
><P
1196
>This test measures the <TT
1197
CLASS="FUNCTION"
1198
>cyg_counter_tick()</TT
1199
> call. A
1200
counter is created that has multiple alarms attached to it. The
1201
purpose of this test is to measure the cost of &#8220;ticking&#8221; a
1202
counter when it has many attached alarms. In this test, the alarms are
1203
not activated (fired).
1204
                </P
1205
></DD
1206
><DT
1207
>Tick &amp; fire counter &#0091;1 alarm&#0093;</DT
1208
><DD
1209
><P
1210
>This test measures the <TT
1211
CLASS="FUNCTION"
1212
>cyg_counter_tick()</TT
1213
> call. A
1214
counter is created that has a single alarm attached to it. The purpose
1215
of this test is to measure the cost of &#8220;ticking&#8221; a counter
1216
when it has a single attached alarm. In this test, the alarm is
1217
activated (fired). Thus the measured time will include the overhead of
1218
calling the alarm callback function.
1219
                </P
1220
></DD
1221
><DT
1222
>Tick &amp; fire counter &#0091;many alarms&#0093;</DT
1223
><DD
1224
><P
1225
>This test measures the <TT
1226
CLASS="FUNCTION"
1227
>cyg_counter_tick()</TT
1228
> call. A
1229
counter is created that has multiple alarms attached to it. The
1230
purpose of this test is to measure the cost of &#8220;ticking&#8221; a
1231
counter when it has many attached alarms. In this test, the alarms are
1232
activated (fired). Thus the measured time will include the overhead of
1233
calling the alarm callback function.
1234
                </P
1235
></DD
1236
><DT
1237
>Alarm latency &#0091;0 threads&#0093;</DT
1238
><DD
1239
><P
1240
>This test attempts to measure the latency in calling an alarm callback
1241
function. The time from the clock interrupt until the alarm function
1242
is called is measured. In this test, there are no threads that can be
1243
run, other than the system idle thread, when the clock interrupt
1244
occurs (all threads are suspended).
1245
                </P
1246
></DD
1247
><DT
1248
>Alarm latency &#0091;2 threads&#0093;</DT
1249
><DD
1250
><P
1251
>This test attempts to measure the latency in calling an alarm callback
1252
function. The time from the clock interrupt until the alarm function
1253
is called is measured. In this test, there are exactly two threads
1254
which are running when the clock interrupt occurs. They are simply
1255
passing back and forth by way of the
1256
<TT
1257
CLASS="FUNCTION"
1258
>cyg_thread_yield()</TT
1259
> call. The purpose of this test
1260
is to measure the variations in the latency when there are executing
1261
threads.
1262
                </P
1263
></DD
1264
><DT
1265
>Alarm latency &#0091;many threads&#0093;</DT
1266
><DD
1267
><P
1268
>This test attempts to measure the latency in calling an alarm callback
1269
function. The time from the clock interrupt until the alarm function
1270
is called is measured. In this test, there are a number of threads
1271
which are running when the clock interrupt occurs. They are simply
1272
passing back and forth by way of the
1273
<TT
1274
CLASS="FUNCTION"
1275
>cyg_thread_yield()</TT
1276
> call. The purpose of this test
1277
is to measure the variations in the latency when there are many
1278
executing threads.
1279
                </P
1280
></DD
1281
></DL
1282
></DIV
1283
></DIV
1284
></DIV
1285
><DIV
1286
CLASS="NAVFOOTER"
1287
><HR
1288
ALIGN="LEFT"
1289
WIDTH="100%"><TABLE
1290
SUMMARY="Footer navigation table"
1291
WIDTH="100%"
1292
BORDER="0"
1293
CELLPADDING="0"
1294
CELLSPACING="0"
1295
><TR
1296
><TD
1297
WIDTH="33%"
1298
ALIGN="left"
1299
VALIGN="top"
1300
><A
1301
HREF="kernel-interrupts.html"
1302
ACCESSKEY="P"
1303
>Prev</A
1304
></TD
1305
><TD
1306
WIDTH="34%"
1307
ALIGN="center"
1308
VALIGN="top"
1309
><A
1310
HREF="ecos-ref.html"
1311
ACCESSKEY="H"
1312
>Home</A
1313
></TD
1314
><TD
1315
WIDTH="33%"
1316
ALIGN="right"
1317
VALIGN="top"
1318
><A
1319
HREF="redboot.html"
1320
ACCESSKEY="N"
1321
>Next</A
1322
></TD
1323
></TR
1324
><TR
1325
><TD
1326
WIDTH="33%"
1327
ALIGN="left"
1328
VALIGN="top"
1329
>Interrupt Handling</TD
1330
><TD
1331
WIDTH="34%"
1332
ALIGN="center"
1333
VALIGN="top"
1334
><A
1335
HREF="kernel.html"
1336
ACCESSKEY="U"
1337
>Up</A
1338
></TD
1339
><TD
1340
WIDTH="33%"
1341
ALIGN="right"
1342
VALIGN="top"
1343
>RedBoot&#8482; User's Guide</TD
1344
></TR
1345
></TABLE
1346
></DIV
1347
></BODY
1348
></HTML
1349
>

powered by: WebSVN 2.1.0

© copyright 1999-2024 OpenCores.org, equivalent to Oliscience, all rights reserved. OpenCores®, registered trademark.