NAME
perf-bench - General framework for benchmark suitesSYNOPSIS
perf bench [<common options>] <subsystem> <suite> [<options>]
DESCRIPTION
This perf bench command is a general framework for benchmark suites.COMMON OPTIONS
-r, --repeat=Specify amount of times to repeat the run
(default 10).
Specify format style. Current available format
styles are:
Default style. This is mainly for human
reading.
% perf bench sched pipe # with no style specified (executing 1000000 pipe operations between two tasks) Total time:5.855 sec 5.855061 usecs/op 170792 ops/sec
This simple style is friendly for automated
processing by scripts.
% perf bench --format=simple sched pipe # specified simple 5.988
SUBSYSTEM
schedScheduler and IPC mechanisms.
System call performance (throughput).
Memory access performance.
NUMA scheduling and MM benchmarks.
Futex stressing benchmarks.
Eventpoll (epoll) stressing benchmarks.
Benchmark internal perf functionality.
All benchmark subsystems.
SUITES FOR sched
messagingSuite for evaluating performance of scheduler
and IPC mechanisms. Based on hackbench by Rusty Russell.
Options of messaging
-p, --pipeUse pipe() instead of socketpair()
Be multi thread instead of multi process
Specify number of groups
Specify number of loops
Example of messaging
% perf bench sched messaging # run with default options (20 sender and receiver processes per group) (10 groups == 400 processes run) Total time:0.308 sec % perf bench sched messaging -t -g 20 # be multi-thread, with 20 groups (20 sender and receiver threads per group) (20 groups == 800 threads run) Total time:0.582 sec
Suite for pipe() system call. Based on
pipe-test-1m.c by Ingo Molnar.
Options of pipe
-l, --loop=Specify number of loops.
Example of pipe
% perf bench sched pipe (executing 1000000 pipe operations between two tasks) Total time:8.091 sec 8.091833 usecs/op 123581 ops/sec % perf bench sched pipe -l 1000 # loop 1000 (executing 1000 pipe operations between two tasks) Total time:0.016 sec 16.948000 usecs/op 59004 ops/sec
SUITES FOR mem
memcpySuite for evaluating performance of simple
memory copy in various ways.
Options of memcpy
-l, --sizeSpecify size of memory to copy (default: 1MB).
Available units are B, KB, MB, GB and TB (case insensitive).
Specify function to copy (default: default).
Available functions are depend on the architecture. On x86-64,
x86-64-unrolled, x86-64-movsq and x86-64-movsb are supported.
Repeat memcpy invocation this number of
times.
Use perf’s cpu-cycles event instead of
gettimeofday syscall.
Suite for evaluating performance of simple
memory set in various ways.
Options of memset
-l, --sizeSpecify size of memory to set (default: 1MB).
Available units are B, KB, MB, GB and TB (case insensitive).
Specify function to set (default: default).
Available functions are depend on the architecture. On x86-64,
x86-64-unrolled, x86-64-stosq and x86-64-stosb are supported.
Repeat memset invocation this number of
times.
Use perf’s cpu-cycles event instead of
gettimeofday syscall.
SUITES FOR numa
memSuite for evaluating NUMA workloads.
SUITES FOR futex
hashSuite for evaluating hash tables.
Suite for evaluating wake calls.
Suite for evaluating parallel wake
calls.
Suite for evaluating requeue calls.
Suite for evaluating futex lock_pi
calls.
SUITES FOR epoll
waitSuite for evaluating concurrent epoll_wait
calls.
Suite for evaluating multiple epoll_ctl
calls.
SUITES FOR internals
synthesizeSuite for evaluating perf’s event
synthesis performance.
SEE ALSO
perf(1)2024-06-21 | perf |