Linux and UNIX Man Pages

Linux & Unix Commands - Search Man Pages

tiobench(1) [debian man page]

tiobench(1)															       tiobench(1)

NAME
tiobench - Threaded I/O bench SYNOPSIS
tiobench [--help] [--nofrag] [--size SizeInMB [--size ...]] [--numruns NumberOfRuns [--numruns ...]] [--dir TestDir [--dir ...]] [--block BlkSizeInBytes [--block ...]] [--random NumberRandOpsPerThread [--random ...]] [--threads NumberOfThreads [--threads ...]] DESCRIPTION
tiobench is a perl wrapper to tiotest calling it multiple times with varying sets of parameters as instructed. OPTIONS --help Display a brief help and exit. --nofrag Instructs tiobench to pass -W to tiotest so it waits for previous threads to finish before starting a new one in the writing phase. For more info see the -W option in the tiotest(1) manpage. --size SizeInMB The total size in MBytes of the files may use together. If this option is not given, tiobench tries to be smart and figure out a size making sense. --numruns NumberOfRuns This number specifies over how many runs each test should be averaged. Defaults to 1. --dir TestDir The directory in which to test. Defaults to ., the current directory. --block BlkSizeInBytes The blocksize in Bytes to use. Defaults to 4096. --random NumberRandOpsPerThread Random I/O operations per thread. Defaults to 1000. --threads NumberOfThreads The number of concurrent test threads. Defaults to 4. The options --size, --numruns, --dir, --block, --random, and --threads may be given multiple times to cover multiple cases, for instance: tiobench --block 4096 --block 8192 will first run through with a 4KB block size and then again with a 8KB block size. To get usefull results the used file sizes should be a lot larger than the physical amount of memory you have. A good idea is to boot with 16 Megs of RAM (Try passing the "mem=16M" option to the kernel to limit Linux to using a very small amount of memory) and into Single User mode only. SEE ALSO
tiotest(1), bonnie(1), hdparm(8) AUTHOR
tiobench was written by James Manning <jmm@computer.org>. This manual page was written by Peter Palfrader <weasel@debian.org>, for the Debian GNU/Linux system (but may be used by others). Mar-2001 tiobench(1)

Check Out this Related Man Page

STRESSAPPTEST(1)					      General Commands Manual						  STRESSAPPTEST(1)

NAME
stressapptest - stress test application for simulating high load situations SYNOPSIS
stressapptest [options] DESCRIPTION
This manual page documents briefly the stressapptest command. stressapptest (unix name for Stressful Application Test) is a program that tries to maximize randomized traffic to memory from processor and I/O, with the intent of creating a realistic high load situation in order to test the existing hardware devices in a computer. OPTIONS
This program supports the following options: -A Run in degraded mode on incompatible systems. -C <threads> Number of memory CPU stress threads to run. -d <device> Add a direct write disk thread with block device (or file) 'device'. -f <filename> Add a disk thread with tempfile 'filename'. -F Don't result check each transaction. -i <threads> Number of memory invert threads to run. -l <logfile> Log output to file 'logfile'. -m <threads> Number of memory copy threads to run. -M <mbytes> Megabytes of RAM to test. -n <ipaddr> Add a network thread connecting to system at 'ipaddr'. -p <pagesize> Size in bytes of memory chunks. -s <seconds> Number of seconds to run. -v <level> Verbosity (0-20), default is 8. -W Use more CPU-stressful memory copy. --blocks-per-segment <number> Number of blocks to read/write per segment per iteration (-d). --cache-size <size> Size of disk cache (-d). --cc_inc_count <number> Number of times to increment the cacheline's member. --cc_line_count <number> Mumber of cache line sized datastructures to allocate for the cache coherency threads to operate. --cc_test Do the cache coherency testing. --destructive Write/wipe disk partition (-d). --filesize <size> Size of disk IO tempfiles. --findfiles Find locations to do disk IO automatically. --force_errors Inject false errors to test error handling. --force_errors_like_crazy Inject a lot of false errors to test error handling. --listen Run threads that listen for incoming net connections. --local_numa Choose memory regions associated with each CPU to be tested by that CPU. --max_errors <number> Exit early after finding specified number of errors. --monitor_mode Only do ECC error polling, no stress load. --no_errors Run without checking for ECC or other errors. --paddr_base <address> Allocate memory starting from this address. --pause_delay <seconds> Delay (in seconds) between power spikes. --pause_duration <seconds> Duration (in seconds) of each pause. --random-threads <number> Number of random threads for each disk write thread (-d). --read-block-size <size> Size of block for reading (-d). --read-threshold <time> Maximum time (in us) a block read should take (-d). --remote_numa <time> Choose memory regions not associated with each CPU to be tested by that CPU. --segment-size <size> Size of segments to split disk into (-d). --stop_on_errors Stop after finding the first error. --write-block-size <size> Size of block for writing (-d). If not defined, the size of block for writing will be defined as the size of block for reading. --write-threshold <time> Maximum time (in us) a block write should take (-d). SEE ALSO
http://code.google.com/p/stressapptest/ AUTHOR
stressapptest was written by Nick Sanders and Rapahel Menderico (Google Inc). This manual page was written by Michael Prokop <mika@debian.org> for the Debian project (and may be used by others). 2009-10-20 STRESSAPPTEST(1)
Man Page