Linux and UNIX Man Pages

Linux & Unix Commands - Search Man Pages

latency(1) [osx man page]

LATENCY(1)						    BSD General Commands Manual 						LATENCY(1)

latency -- monitors scheduling and interrupt latency SYNOPSIS
latency [-p] [-h] [-m] [-st threshold] [-it threshold] [-c code_file] [-l log_file] [-R raw_file] [-n kernel] DESCRIPTION
The latency utility provides scheduling and interrupt-latency statistics. Due to the kernel tracing facility it uses to operate, the command requires root privileges. The arguments are as follows: -c code_file When the -c option is specified, it takes a path to a code file that contains the mappings for the system calls. This option over- rides the default location of the system call code file, which is found in /usr/share/misc/ -h Display high resolution interrupt latencies and write them to latencies.csv (truncate existing file) upon exit. -m Display per-CPU interrupt latency statistics. -it threshold Set the interrupt latency threshold, expressed in microseconds. If the latency exceeds this value, and a log file has been speci- fied, a record of what occurred during this time is recorded. -l log_file Specifies a log file that is written to when either the interrupt or scheduling latency is exceeded. -n kernel By default, latency acts on the default /mach_kernel. This option allows you to specify an alternate booted kernel. -p priority Specifies the priority level to observe scheduler latencies for. -st threshold Set the scheduler latency threshold in microseconds. If latency exceeds this, and a log file has been specified, a record of what occurred during this time is recorded. -R raw_file Specifies a raw trace file to use as input. 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 -p 97 -st 20000 -it 1000 -l /var/tmp/latency.log The latency utility will watch threads with priority 97 for scheduling latencies. The threshold for the scheduler is set to 20000 microsec- onds. The threshold for interrupts is set to 1000 microseconds. Latencies that exceed these thresholds will be logged in /var/tmp/latency.log. SEE ALSO
fs_usage(1), sc_usage(1), top(1) Mac OS X March 28, 2000 Mac OS X

Check Out this Related Man Page

lgrp_latency(3LGRP)													       lgrp_latency(3LGRP)

lgrp_latency, lgrp_latency_cookie - get latency between two lgroups SYNOPSIS
cc [ flag... ] file... -llgrp [ library... ] #include <sys/lgrp_user.h> int lgrp_latency_cookie(lgrp_cookie_t cookie, lgrp_id_t from, lgrp_id_t to, lgrp_lat_between_t between); int lgrp_latency(lgrp_id_t from, lgrp_id_t to); The lgrp_latency_cookie() function takes a cookie representing a snapshot of the lgroup hierarchy obtained from lgrp_init(3LGRP) and returns the latency value between a hardware resource in the from lgroup to a hardware resource in the to lgroup. If from is the same lgroup as to, the latency value within that lgroup is returned. The between argument should be set to the following value to specify between which hardware resources the latency should be measured: LGRP_LAT_CPU_TO_MEM /* latency from CPU to memory */ The latency value is defined by the operating system and is platform-specific. It can be used only for relative comparison of lgroups on the running system. It does not necessarily represent the actual latency between hardware devices, and it might not be applicable across platforms. The lgrp_latency() function is similiar to the lgrp_latency_cookie() function, but returns the latency between the given lgroups at the given instant in time. Since lgroups can be freed and reallocated, this function might not be able to provide a consistent answer across calls. For that reason, the lgrp_latency_cookie() function should be used in its place. Upon successful completion, the latency value is returned. Otherwise -1 is returned and errno is set to indicate the error. The lgrp_latency_cookie() and lgrp_latency() functions will fail if: EINVAL The specified cookie, lgroup ID, or value given for the between argument is not valid. ESRCH The specified lgroup ID was not found, the from lgroup does not contain any CPUs, or the to lgroup does not have any mem- ory. See attributes(5) for descriptions of the following attributes: +-----------------------------+-----------------------------+ | ATTRIBUTE TYPE | ATTRIBUTE VALUE | +-----------------------------+-----------------------------+ |Interface Stability |Evolving | +-----------------------------+-----------------------------+ |MT-Level |MT-Safe | +-----------------------------+-----------------------------+ lgrp_init(3LGRP), lgrp_parents(3LGRP), lgrp_children(3LGRP), liblgrp(3LIB), attributes(5) 26 Jan 2005 lgrp_latency(3LGRP)
Man Page