cyclictest 主要是用于测试系统延时，进而判断系统的实时性

使用版本

rt-tests-2.6.tar.gz
numactl v2.0.16

问题

编译时，需要先编译 numactl ，不然会有以下报错：

arm-linux-gnueabihf-gcc -D VERSION=2.6 -c src/cyclictest/cyclictest.c -Wall -Wno-nonnull -Wextra -O2 -g -D_GNU_SOURCE -Isrc/include   -o bld/cyclictest.o
In file included from src/cyclictest/cyclictest.c:33:
src/cyclictest/rt_numa.h:18:10: fatal error: numa.h: 没有那个文件或目录#include <numa.h>^~~~~~~~
compilation terminated.
Makefile:106: recipe for target 'bld/cyclictest.o' failed
make: *** [bld/cyclictest.o] Error 1

编译 numactl

文件下载 https://github.com/numactl/numactl/tree/v2.0.16

编译命令：

./autogen.sh
./configure CC=arm-linux-gnueabihf-gcc --host=arm  prefix=~/git/numactl-2.0.16/build
make install

这是主要用到编译生成的 lib 及 include 里的文件

编译 cyclictest

下载文件 ：

https://git.kernel.org/pub/scm/utils/rt-tests/rt-tests.git/

打开 Makefile 文件：

在 RTTESTLIB 后面加上 -L/home/XXX/git/numactl-2.0.16/build/lib
在 CPPFLAGS 后面加上 -I/home/XXX/git/numactl-2.0.16/build/include

RTTESTLIB = -lrttest -L$(OBJDIR) -L/home/XXX/git/numactl-2.0.16/build/lib
CPPFLAGS += -D_GNU_SOURCE -Isrc/include  -I/home/XXX/git/numactl-2.0.16/build/include

然后使用编译命令

make CROSS_COMPILE=arm-linux-gnueabihf- LDFLAGS=-static

即可在目录中看到 cyclictest

使用

cyclictest V 2.60
Usage:
cyclictest <options>-a [CPUSET] --affinity     Run thread #N on processor #N, if possible, or if CPUSETgiven, pin threads to that set of processors in round-robin order.  E.g. -a 2 pins all threads to CPU 2,but -a 3-5,0 -t 5 will run the first and fifththreads on CPU (0),thread #2 on CPU 3, thread #3on CPU 4, and thread #5 on CPU 5.
-A USEC  --aligned=USEC    align thread wakeups to a specific offset
-b USEC  --breaktrace=USEC send break trace command when latency > USEC
-c CLOCK --clock=CLOCK     select clock0 = CLOCK_MONOTONIC (default)1 = CLOCK_REALTIME--default-system  Don't attempt to tune the system from cyclictest.Power management is not suppressed.This might give poorer results, but will allow youto discover if you need to tune the system
-d DIST  --distance=DIST   distance of thread intervals in us, default=500
-D       --duration=TIME   specify a length for the test run.Append 'm', 'h', or 'd' to specify minutes, hours or days.
-F       --fifo=<path>     create a named pipe at path and write stats to it
-h       --histogram=US    dump a latency histogram to stdout after the runUS is the max latency time to be tracked in microsecondsThis option runs all threads at the same priority.
-H       --histofall=US    same as -h except with an additional summary column--histfile=<path> dump the latency histogram to <path> instead of stdout
-i INTV  --interval=INTV   base interval of thread in us default=1000--json=FILENAME   write final results into FILENAME, JSON formatted--laptop          Save battery when running cyclictestThis will give you poorer realtime resultsbut will not drain your battery so quickly--latency=PM_QOS  power management latency target valueThis value is written to /dev/cpu_dma_latencyand affects c-states. The default is 0
-l LOOPS --loops=LOOPS     number of loops: default=0(endless)--mainaffinity=CPUSETRun the main thread on CPU #N. This only affectsthe main thread and not the measurement threads
-m       --mlockall        lock current and future memory allocations
-M       --refresh_on_max  delay updating the screen until a new maxlatency is hit. Useful for low bandwidth.
-N       --nsecs           print results in ns instead of us (default us)
-o RED   --oscope=RED      oscilloscope mode, reduce verbose output by RED
-p PRIO  --priority=PRIO   priority of highest prio thread--policy=NAME     policy of measurement thread, where NAME may be oneof: other, normal, batch, idle, fifo or rr.--priospread      spread priority levels starting at specified value
-q       --quiet           print a summary only on exit
-r       --relative        use relative timer instead of absolute
-R       --resolution      check clock resolution, calling clock_gettime() manytimes.  List of clock_gettime() values will bereported with -X--secaligned [USEC] align thread wakeups to the next full secondand apply the optional offset
-s       --system          use sys_nanosleep and sys_setitimer
-S       --smp             Standard SMP testing: options -a -t and same priorityof all threads--spike=<trigger>  record all spikes > trigger--spike-nodes=[num of nodes]These are the maximum number of spikes we can record.The default is 1024 if not specified
-t       --threads         one thread per available processor
-t [NUM] --threads=NUM     number of threads:without NUM, threads = max_cpuswithout -t default = 1--tracemark       write a trace mark when -b latency is exceeded
-u       --unbuffered      force unbuffered output for live processing
-v       --verbose         output values on stdout for statisticsformat: n:c:v n=tasknum c=count v=value in us--dbg_cyclictest  print info useful for debugging cyclictest
-x       --posix_timers    use POSIX timers instead of clock_nanosleep.

使用命令

./cyclictest  -S -p 95  -D 1m -m -i 1000 -d 0

-S 为每个核一个线程，-D 执行一分钟

---

./cyclictest   -p 95  -D 1m -m -i 1000 -d 0 -t 10 -a 5-7

-t 设置 10 个线程， -a 设置在核 5-7上跑

T:   线程序号
P:   线程优先级
C:   线程执行次数
I:   线程运行间隔(us)
Min: 最小延时(us)
Act: 最近一次的延时(us)
Avg：平均延时(us)
Max：最大延时(us)

参考

https://github.com/CJTSAJ/jailhouse-learning/blob/master/%E4%BA%A4%E5%8F%89%E7%BC%96%E8%AF%91cyclictest.md
https://zhuanlan.zhihu.com/p/336381111