Scott Anderson | b0114cb | 2012-04-09 14:08:22 -0700 | [diff] [blame] | 1 | .TH STRESSAPPTEST 1 2009-10-20 |
| 2 | .SH NAME |
| 3 | stressapptest \- stress test application for simulating high load situations |
| 4 | .SH SYNOPSIS |
| 5 | .B stressapptest |
| 6 | .RI [ options ] |
| 7 | .SH DESCRIPTION |
| 8 | This manual page documents briefly the |
| 9 | .B stressapptest |
| 10 | command. |
| 11 | .PP |
| 12 | \fBstressapptest\fP (unix name for Stressful Application Test) is a program that |
| 13 | tries to maximize randomized traffic to memory from processor and I/O, with the |
| 14 | intent of creating a realistic high load situation in order to test the existing |
| 15 | hardware devices in a computer. |
| 16 | .SH OPTIONS |
| 17 | This program supports the following options: |
| 18 | |
| 19 | .TP |
| 20 | .B \-A |
| 21 | Run in degraded mode on incompatible systems. |
| 22 | |
| 23 | .TP |
| 24 | .B \-C <threads> |
| 25 | Number of memory CPU stress threads to run. |
| 26 | |
| 27 | .TP |
| 28 | .B \-d <device> |
| 29 | Add a direct write disk thread with block device (or file) 'device'. |
| 30 | |
| 31 | .TP |
| 32 | .B \-f <filename> |
| 33 | Add a disk thread with tempfile 'filename'. |
| 34 | |
| 35 | .TP |
| 36 | .B \-F |
| 37 | Don't result check each transaction. |
| 38 | |
| 39 | .TP |
| 40 | .B \-i <threads> |
| 41 | Number of memory invert threads to run. |
| 42 | |
| 43 | .TP |
| 44 | .B \-l <logfile> |
| 45 | Log output to file 'logfile'. |
| 46 | |
| 47 | .TP |
| 48 | .B \-m <threads> |
| 49 | Number of memory copy threads to run. |
| 50 | |
| 51 | .TP |
| 52 | .B \-M <mbytes> |
| 53 | Megabytes of RAM to test. |
| 54 | |
| 55 | .TP |
| 56 | .B \-n <ipaddr> |
| 57 | Add a network thread connecting to system at 'ipaddr'. |
| 58 | |
| 59 | .TP |
| 60 | .B \-p <pagesize> |
| 61 | Size in bytes of memory chunks. |
| 62 | |
| 63 | .TP |
| 64 | .B \-s <seconds> |
| 65 | Number of seconds to run. |
| 66 | |
| 67 | .TP |
| 68 | .B \-v <level> |
| 69 | Verbosity (0-20), default is 8. |
| 70 | |
| 71 | .TP |
| 72 | .B \-W |
| 73 | Use more CPU-stressful memory copy. |
| 74 | |
| 75 | .TP |
| 76 | .B \-\-blocks\-per\-segment <number> |
| 77 | Number of blocks to read/write per segment per iteration (\-d). |
| 78 | |
| 79 | .TP |
| 80 | .B \-\-cache\-size <size> |
| 81 | Size of disk cache (\-d). |
| 82 | |
| 83 | .TP |
| 84 | .B \-\-cc_inc_count <number> |
| 85 | Number of times to increment the cacheline's member. |
| 86 | |
| 87 | .TP |
| 88 | .B \-\-cc_line_count <number> |
| 89 | Mumber of cache line sized datastructures to allocate for the cache coherency |
| 90 | threads to operate. |
| 91 | |
| 92 | .TP |
| 93 | .B \-\-cc_test |
| 94 | Do the cache coherency testing. |
| 95 | |
| 96 | .TP |
| 97 | .B \-\-destructive |
| 98 | Write/wipe disk partition (\-d). |
| 99 | |
| 100 | .TP |
| 101 | .B \-\-filesize <size> |
| 102 | Size of disk IO tempfiles. |
| 103 | |
| 104 | .TP |
| 105 | .B \-\-findfiles |
| 106 | Find locations to do disk IO automatically. |
| 107 | |
| 108 | .TP |
| 109 | .B \-\-force_errors |
| 110 | Inject false errors to test error handling. |
| 111 | |
| 112 | .TP |
| 113 | .B \-\-force_errors_like_crazy |
| 114 | Inject a lot of false errors to test error handling. |
| 115 | |
| 116 | .TP |
| 117 | .B \-\-listen |
| 118 | Run threads that listen for incoming net connections. |
| 119 | |
| 120 | .TP |
| 121 | .B \-\-local_numa |
| 122 | Choose memory regions associated with each CPU to be tested by that CPU. |
| 123 | |
| 124 | .TP |
| 125 | .B \-\-max_errors <number> |
| 126 | Exit early after finding specified number of errors. |
| 127 | |
| 128 | .TP |
| 129 | .B \-\-monitor_mode |
| 130 | Only do ECC error polling, no stress load. |
| 131 | |
| 132 | .TP |
| 133 | .B \-\-no_errors |
| 134 | Run without checking for ECC or other errors. |
| 135 | |
| 136 | .TP |
| 137 | .B \-\-paddr_base <address> |
| 138 | Allocate memory starting from this address. |
| 139 | |
| 140 | .TP |
| 141 | .B \-\-pause_delay <seconds> |
| 142 | Delay (in seconds) between power spikes. |
| 143 | |
| 144 | .TP |
| 145 | .B \-\-pause_duration <seconds> |
| 146 | Duration (in seconds) of each pause. |
| 147 | |
| 148 | .TP |
| 149 | .B \-\-random-threads <number> |
| 150 | Number of random threads for each disk write thread (\-d). |
| 151 | |
| 152 | .TP |
| 153 | .B \-\-read-block-size <size> |
| 154 | Size of block for reading (\-d). |
| 155 | |
| 156 | .TP |
| 157 | .B \-\-read-threshold <time> |
| 158 | Maximum time (in us) a block read should take (\-d). |
| 159 | |
| 160 | .TP |
| 161 | .B \-\-remote_numa <time> |
| 162 | Choose memory regions not associated with each CPU to be tested by that CPU. |
| 163 | |
| 164 | .TP |
| 165 | .B \-\-segment-size <size> |
| 166 | Size of segments to split disk into (\-d). |
| 167 | |
| 168 | .TP |
| 169 | .B \-\-stop_on_errors |
| 170 | Stop after finding the first error. |
| 171 | |
| 172 | .TP |
| 173 | .B \-\-write-block-size <size> |
| 174 | Size of block for writing (\-d). If not defined, the size of block for writing |
| 175 | will be defined as the size of block for reading. |
| 176 | |
| 177 | .TP |
| 178 | .B \-\-write-threshold <time> |
| 179 | Maximum time (in us) a block write should take (\-d). |
| 180 | |
| 181 | .SH SEE ALSO |
| 182 | .BR http://code.google.com/p/stressapptest/ |
| 183 | .SH AUTHOR |
| 184 | stressapptest was written by Nick Sanders and Rapahel Menderico (Google Inc). |
| 185 | .PP |
| 186 | This manual page was written by Michael Prokop <mika@debian.org> |
| 187 | for the Debian project (and may be used by others). |