Linux and UNIX Man Pages

Linux & Unix Commands - Search Man Pages

hwlatdetect(8) [debian man page]

HWLATDETECT(8)						      System Manager's Manual						    HWLATDETECT(8)

NAME
hwlatdetect - program to control the kernel hardware latency detection module SYNOPSIS
hwlatdetect [ --duration=<time> ] [--threshold=<usecs> ] [--window=<time interval> ] [--width=<time interval> ] [--report=<path> ] [--cleanup ] [--debug ] [--quiet ] DESCRIPTION
hwlatdetect is a program that controls the kernel hardware latency detector module (hwlat_detector.ko). The module is a special purpose kernel module that is used to detect large system latencies induced by the behavior of certain underlying hardware or firmware, independent of Linux itself. The code was developed originally to detect SMIs (System Management Interrupts) on x86 systems, however there is nothing x86 specific about this patchset. It was originally written for use by the "RT" patch since the Real Time kernel is highly latency sensi- tive. SMIs are usually not serviced by the Linux kernel, which typically does not even know that they are occuring. SMIs are instead are set up by BIOS code and are serviced by BIOS code, usually for "critical" events such as management of thermal sensors and fans. Sometimes though, SMIs are used for other tasks and those tasks can spend an inordinate amount of time in the handler (sometimes measured in milliseconds). Obviously this is a problem if you are trying to keep event service latencies down in the microsecond range. The hardware latency detector module works by hogging all of the cpus for configurable amounts of time (by calling stop_machine()), polling the CPU Time Stamp Counter for some period, then looking for gaps in the TSC data. Any gap indicates a time when the polling was inter- rupted and since the machine is stopped and interrupts turned off the only thing that could do that would be an SMI. The hwlatdetector script manages the mounting/unmounting of the debugfs as well as the loading/unloading of the hwlat_detector module. If the debugfs is already mounted then hwlatdetector will not unmount it after a run. Likewise, if the hwlat_detector module is already loaded, it will not be unloaded after a run. OPTIONS
--duration=<time>{s,m,d} Run the detector logic in for the specified duration. The duration is a base 10 integer number that defaults to a value in seconds. An optional suffix may be specified to indicate minutes, hours or days. --threshold=<microsecond value> Specify the TSC gap used to detect an SMI. Any gap value greater than <theshold> is considered to be the result of an SMI occuring. --window=<time value>{us,ms,s,m,d} specify the size of the sample window. Converted to microseconds when passed to the kernel module. --width=<time value>{us,ms,s,m,d} The amount of time within the sample window where the detector is actually sampling. Must be less than the --window value. --report=FILENAME Specify the output filename of the detector report. Default behavior is to print to standard output --cleanup Force unload of hwlat_detector.ko and unmounting of debugfs filesystem. --debug Turn on debug prints --quiet Turn off all information prints AUTHOR
hwlatdetect was written by Clark Williams <williams@redhat.com> hwlat_detector.ko was written by Jon Masters <jcm@redhat.com> May 12, 2009 HWLATDETECT(8)

Check Out this Related Man Page

TONEDEBUG(1)						    Voicetronix Telephony Tools 					      TONEDEBUG(1)

NAME
tonedebug - Test parameters for the libvpb programmable tone detector SYNOPSIS
tonedebug [options] DESCRIPTION
The tonedebug utility assists with quickly testing tone detector parameters against the signals they are intended to detect. It has three main modes of operation for testing single continuous or pulsed tones, or for testing a set of tones specified in the environment. OPTIONS
The following common options apply for all modes: --card number Explicitly select the card to test. Default is card 0. --port number Explicitly select the port to test. Default is port 0 of the card being tested. -w wavfile Specify a wav file to play the tones from. For OpenLine and OpenSwitch cards it should be played to an FXO port with no phone line connected, and the tone detector will process the reflected signal from the hybrid circuit. The OpenPCI cards have almost no echo from this circuit, but an on hook phone connected to an FXS port should produce a detectable echo signal. -s filename.c Writes out a C function that can be included in your own code to configure the tone generator with the settings being tested. Environment options To run tonedebug using the settings specified with the VPB_TONE environment variables, call it with the -e option. For example: $ tonedebug -e --port 4 -w my.wav Will use the enviroment settings to try and detect tones from my.wav played into port 4 of card 0. There are no other options specific to this mode. Continuous tone options If passed the -c option, then the tonedebug utility will test parameters suitable for a continuous tone. For example: $ tonedebug -c 425 100 2000 -w dialtone.wav -t dial Will try to detect 2 seconds of 425Hz tone from dialtone.wav, played into port 0 of card 0. If it succeeds it will report a dial event. The following additional options may be used in this mode: -c center-freq bandwidth duration Specifies the primary tone characteristics, its frequency and bandwidth in Hz. and its minimum duration in milliseconds. -d center-freq2 bandwidth2 Specifies the second tone of a multi-frequency tone. -q twist Specifies the twist of a multi-frequency tone. -n snr Specifies the acceptable signal to noise ratio, in dB. -t dial | busy | ringback Specifies the name of a predefined tone to replace with the given settings. Pulsed tone options The -p options will enable testing for pulsed tones. In addition to the common options and the options for continuous tones, the following options are supported in this mode: -p center-freq bandwidth on-time Specifies the primary tone characteristics, its frequency and bandwidth in Hz. and its 'on' time in milliseconds. -off off-time The 'off' time of the pulse in milliseconds. SEE ALSO
tonetrain(1) BUGS
We rely on an echo from the hardware to feed the signal into the tone detector. This should be fixed to feed it in directly at some stage in the future. AUTHOR
Ron Lee, David Rowe, Voicetronix <support@voicetronix.com.au> This manual page was written by Ron <ron@debian.org>, for the Debian project (but may be used by others). VPB driver package Feb 2, 2007 TONEDEBUG(1)
Man Page