PERF−BENCH - Online Linux Manual PageSection : 1
Updated : 03/30/2021
Source : perf
Note : perf Manual
NAMEperf-bench − General framework for benchmark suites
SYNOPSISperf bench [<common options>] <subsystem> <suite> [<options>]
DESCRIPTIONThis perf bench command is a general framework for benchmark suites.
COMMON OPTIONS−r, −−repeat= Specify amount of times to repeat the run (default 10). −f, −−format= Specify format style. Current available format styles are: default Default style. This is mainly for human reading. .ft C
% 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
.ft
simple This simple style is friendly for automated processing by scripts. .ft C
% perf bench −−format=simple sched pipe # specified simple
5.988
.ft
SUBSYSTEMsched Scheduler and IPC mechanisms. syscall System call performance (throughput). mem Memory access performance. numa NUMA scheduling and MM benchmarks. futex Futex stressing benchmarks. epoll Eventpoll (epoll) stressing benchmarks. internals Benchmark internal perf functionality. all All benchmark subsystems.
SUITES FOR schedmessaging Suite for evaluating performance of scheduler and IPC mechanisms. Based on hackbench by Rusty Russell. .it 1 an-trap
¶Options of messaging −p, −−pipe Use pipe() instead of socketpair() −t, −−thread Be multi thread instead of multi process −g, −−group= Specify number of groups −l, −−nr_loops= Specify number of loops .it 1 an-trap
¶Example of messaging .ft C
% 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
.ft
pipe Suite for pipe() system call. Based on pipe−test−1m.c by Ingo Molnar. .it 1 an-trap
¶Options of pipe −l, −−loop= Specify number of loops. .it 1 an-trap
¶Example of pipe .ft C
% 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
.ft
SUITES FOR syscallbasic Suite for evaluating performance of core system call throughput (both usecs/op and ops/sec metrics). This uses a single thread simply doing getppid(2), which is a simple syscall where the result is not cached by glibc.
SUITES FOR memmemcpy Suite for evaluating performance of simple memory copy in various ways. .it 1 an-trap
¶Options of memcpy −l, −−size Specify size of memory to copy (default: 1MB). Available units are B, KB, MB, GB and TB (case insensitive). −f, −−function 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. −l, −−nr_loops Repeat memcpy invocation this number of times. −c, −−cycles Use perf’s cpu−cycles event instead of gettimeofday syscall. memset Suite for evaluating performance of simple memory set in various ways. .it 1 an-trap
¶Options of memset −l, −−size Specify size of memory to set (default: 1MB). Available units are B, KB, MB, GB and TB (case insensitive). −f, −−function 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. −l, −−nr_loops Repeat memset invocation this number of times. −c, −−cycles Use perf’s cpu−cycles event instead of gettimeofday syscall.
SUITES FOR numamem Suite for evaluating NUMA workloads.
SUITES FOR futexhash Suite for evaluating hash tables. wake Suite for evaluating wake calls. wake−parallel Suite for evaluating parallel wake calls. requeue Suite for evaluating requeue calls. lock−pi Suite for evaluating futex lock_pi calls.
SUITES FOR epollwait Suite for evaluating concurrent epoll_wait calls. ctl Suite for evaluating multiple epoll_ctl calls.
SUITES FOR internalssynthesize Suite for evaluating perf’s event synthesis performance.
SEE ALSOperf(1) 0
Johanes Gumabo
Data Size : 27,201 byte
man-perf-bench.1Build : 2024-12-05, 20:55 :
Visitor Screen : x
Visitor Counter ( page / site ) : 2 / 202,066
Visitor ID : :
Visitor IP : 18.226.166.207 :
Visitor Provider : AMAZON-02 :
Provider Position ( lat x lon ) : 39.962500 x -83.006100 : x
Provider Accuracy Radius ( km ) : 1000 :
Provider City : Columbus :
Provider Province : Ohio , : ,
Provider Country : United States :
Provider Continent : North America :
Visitor Recorder : Version :
Visitor Recorder : Library :
Online Linux Manual Page : Version : Online Linux Manual Page - Fedora.40 - march=x86-64 - mtune=generic - 24.12.05
Online Linux Manual Page : Library : lib_c - 24.10.03 - march=x86-64 - mtune=generic - Fedora.40
Online Linux Manual Page : Library : lib_m - 24.10.03 - march=x86-64 - mtune=generic - Fedora.40
Data Base : Version : Online Linux Manual Page Database - 24.04.13 - march=x86-64 - mtune=generic - fedora-38
Data Base : Library : lib_c - 23.02.07 - march=x86-64 - mtune=generic - fedora.36
Very long time ago, I have the best tutor, Wenzel Svojanovsky . If someone knows the email address of Wenzel Svojanovsky , please send an email to johanes_gumabo@yahoo.co.id .
If error, please print screen and send to johanes_gumabo@yahoo.co.id
Under development. Support me via PayPal.
ERROR : Need New Coding : (parse_manual_page_|249|perf-bench.1|142|it|.it 1 an-trap
) (parse_manual_page_|249|perf-bench.1|171|it|.it 1 an-trap
) (parse_manual_page_|249|perf-bench.1|209|it|.it 1 an-trap
) (parse_manual_page_|249|perf-bench.1|223|it|.it 1 an-trap
) (parse_manual_page_|249|perf-bench.1|270|it|.it 1 an-trap
) (parse_manual_page_|249|perf-bench.1|304|it|.it 1 an-trap
)