1STRESSAPPTEST(1)            General Commands Manual           STRESSAPPTEST(1)
2
3
4

NAME

6       stressapptest - stress test application for simulating high load situa‐
7       tions
8

SYNOPSIS

10       stressapptest [options]
11

DESCRIPTION

13       This manual page documents briefly the stressapptest command.
14
15       stressapptest (unix name for Stressful Application Test) is  a  program
16       that  tries to maximize randomized traffic to memory from processor and
17       I/O, with the intent of creating a realistic high load situation in or‐
18       der to test the existing hardware devices in a computer.
19

OPTIONS

21       This program supports the following options:
22
23
24       -A     Run in degraded mode on incompatible systems.
25
26
27       -C <threads>
28              Number of memory CPU stress threads to run.
29
30
31       -d <device>
32              Add  a direct write disk thread with block device (or file) 'de‐
33              vice'.
34
35
36       -f <filename>
37              Add a disk thread with tempfile 'filename'.
38
39
40       -F     Don't result check each transaction.
41
42
43       -i <threads>
44              Number of memory invert threads to run.
45
46
47       -l <logfile>
48              Log output to file 'logfile'.
49
50
51       -m <threads>
52              Number of memory copy threads to run.
53
54
55       -M <mbytes>
56              Megabytes of RAM to test.
57
58
59       -n <ipaddr>
60              Add a network thread connecting to system at 'ipaddr'.
61
62
63       -p <pagesize>
64              Size in bytes of memory chunks.
65
66
67       -s <seconds>
68              Number of seconds to run.
69
70
71       -v <level>
72              Verbosity (0-20), default is 8.
73
74
75       -W     Use more CPU-stressful memory copy.
76
77
78       --blocks-per-segment <number>
79              Number of blocks to read/write per segment per iteration (-d).
80
81
82       --cache-size <size>
83              Size of disk cache (-d).
84
85
86       --cc_inc_count <number>
87              Number of times to increment the cacheline's member.
88
89
90       --cc_line_count <number>
91              Number of cache line sized datastructures to  allocate  for  the
92              cache coherency threads to operate.
93
94
95       --cc_line_size <number>
96              Size  of cache line to use as the basis for cache coherency test
97              data structures.
98
99
100       --cc_test
101              Do the cache coherency testing.
102
103
104       --destructive
105              Write/wipe disk partition (-d).
106
107
108       --filesize <size>
109              Size of disk IO tempfiles.
110
111
112       --findfiles
113              Find locations to do disk IO automatically.
114
115
116       --force_errors
117              Inject false errors to test error handling.
118
119
120       --force_errors_like_crazy
121              Inject a lot of false errors to test error handling.
122
123
124       --listen
125              Run threads that listen for incoming net connections.
126
127
128       --local_numa
129              Choose memory regions associated with each CPU to be  tested  by
130              that CPU.
131
132
133       --max_errors <number>
134              Exit early after finding specified number of errors.
135
136
137       --monitor_mode
138              Only do ECC error polling, no stress load.
139
140
141       --no_errors
142              Run without checking for ECC or other errors.
143
144
145       --paddr_base <address>
146              Allocate memory starting from this address.
147
148
149       --pause_delay <seconds>
150              Delay (in seconds) between power spikes.
151
152
153       --pause_duration <seconds>
154              Duration (in seconds) of each pause.
155
156
157       --random-threads <number>
158              Number of random threads for each disk write thread (-d).
159
160
161       --read-block-size <size>
162              Size of block for reading (-d).
163
164
165       --read-threshold <time>
166              Maximum time (in us) a block read should take (-d).
167
168
169       --remote_numa <time>
170              Choose  memory regions not associated with each CPU to be tested
171              by that CPU.
172
173
174       --segment-size <size>
175              Size of segments to split disk into (-d).
176
177
178       --stop_on_errors
179              Stop after finding the first error.
180
181
182       --write-block-size <size>
183              Size of block for writing (-d). If  not  defined,  the  size  of
184              block for writing will be defined as the size of block for read‐
185              ing.
186
187
188       --write-threshold <time>
189              Maximum time (in us) a block write should take (-d).
190
191

SEE ALSO

193       http://code.google.com/p/stressapptest/
194

AUTHOR

196       stressapptest was written by Nick Sanders and Rapahel Menderico (Google
197       Inc).
198
199       This  manual  page  was written by Michael Prokop <mika@debian.org> for
200       the Debian project (and may be used by others).
201
202
203
204                                  2009-10-20                  STRESSAPPTEST(1)
Impressum