latency(1) [opendarwin man page]
LATENCY(1) BSD General Commands Manual LATENCY(1) NAME
latency -- monitors scheduling and interrupt latency SYNOPSIS
latency [-rt] [-c codefile] [-l logfile] [-st threshold] [-it threshold] [-s sleep_in_usecs] [-d decrementer_in_usecs] [-n kernel] DESCRIPTION
The latency utility provides scheduling and interrupt latency statistics. It requires root privileges due to the kernel tracing facility it uses to operate. The arguments are as follows: -rt Set real time scheduling policy. Default policy is timeshare. -c When the -c option is specified, it takes a path to a codefile that contains the mappings for the system calls. This option over- rides the default location of the system call codefile which is found in /usr/share/misc/trace.codes. -l Specifies a logfile that is written to when either the interrupt or scheduling latency is exceeded. -st Set the scheduler latency threshold in microseconds. If latency exceeds this, and a logfile has been specified, a record of what occurred during this time is recorded. -it Set the interrupt latency threshold in microseconds. If latency exceeds this, and a logfile has been specified, a record of what occurred during this time is recorded. -s The -s option sets the timer. It takes microseconds as an argument, the default timer is set to 1000 microseconds. -d The -d option sets the decrementer. It takes microseconds as an argument. The decrementer is set back to the system default on exit. -n By default, latency acts on the default /mach_kernel. This option allows you to specify an alternate booted kernel. The data columns displayed are as follows: SCHEDULER The number of context switches that fall within the described delay. INTERRUPTS The number of interrupts that fall within the described delay. The latency utility is also SIGWINCH savvy, so adjusting your window geometry will change the list of delay values displayed. SAMPLE USAGE
latency -rt -st 20000 -it 1000 -l /var/tmp/latency.log The latency utility will set the realtime scheduling policy. The threshold for the scheduler is set to 20000 microseconds. The threshold for interrupts is set to 1000 microseconds. Latencies that exceed these thresholds will be logged in /var/tmp/latency.log. SEE ALSO
top(1), fs_usage(1), sc_usage(1) Mac OS X March 28, 2000 Mac OS X
Check Out this Related Man Page
SC_USAGE(1) BSD General Commands Manual SC_USAGE(1) NAME
sc_usage -- show system call usage statistics SYNOPSIS
sc_usage [-c codefile] [-e] [-l] [-s interval] pid | cmd | -E execute DESCRIPTION
sc_usage displays an ongoing sample of system call and page fault usage statistics for a given process in a ``top-like'' fashion. It requires root privileges due to the kernel tracing facility it uses to operate. Page faults can be of the following types: PAGE_IN page had to read from disk ZERO_FILL page was created and zero filled COW page was copied from another page CACHE_HIT page was found in the cache The arguments are as follows: -c When the -c option is specified, it expects a path to a codefile that contains the mappings for the system calls. This option over- rides the default location of the system call codefile which is found in /usr/share/misc/trace.codes. -e Specifying the -e option generates output that is sorted by call count. This overrides the default sort by time. -l The -l option causes sc_usage to turn off its continuous window updating style of output and instead output as a continuous scrolling of data. -s By default, sc_usage updates its output at one second intervals. This sampling interval may be changed by specifying the -s option. Enter the interval in seconds. pid | cmd | -E execute The last argument must be a process id, a running command name, or using the -E option, an execution path followed by optional argu- ments. The system call usage data for the process or command is displayed. If the -E flag is used, sc_usage will launch the exe- cutable, pass along any optional arguments and display system call usage date for that executable. The data columns displayed are as follows: TYPE the system call type NUMBER the system call count CPU_TIME the amount of cpu time consumed WAIT_TIME the absolute time the process is waiting CURRENT_TYPE the current system call type LAST_PATHNAME_WAITED_FOR for each active thread, the last pathname that was referenced by a system call that blocked CUR_WAIT_TIME the cumulative time that a thread has been blocked THRD# the thread number PRI current scheduling priority The sc_usage command also displays some global state in the first few lines of output, including the number of preemptions, context switches, threads, faults and system calls, found during the sampling period. The current time and the elapsed time that the command has been running is also displayed here. The sc_usage command is also SIGWINCH savvy, so adjusting your window geometry may change the list of system calls being displayed. Typing a 'q' will cause sc_usage to exit immediately. Typing any other character will cause sc_usage to reset its counters and the display. SAMPLE USAGE
sc_usage Finder -e -s2 sc_usage will sort the Finder process usage data according to system call count and update the output at 2 second intervals. SEE ALSO
fs_usage(1), latency(1), top(1) Mac OS X October 28, 2002 Mac OS X