昨天发了个sysbench跑分的帖子哪去啦？

太阳

        跑分是优化内核和比对系统性能的基本方法之一，大家玩到一定程度应该不会再陶醉于刷一个别人做的img，会开始琢磨自己作个内核，裁减个系统啥的，但这不是个轻松活路，谁都不大可能有时间做出所有可能，比对完所有内核和系统，人多力量大。咱一起找找什么样的系统什么性能更优，更适合做什么样的应用，欢迎大家一起来加油！
       昨天找了个方便的跑分软件，测试系统：内核sunxi－linux3.4，rootfs ubuntu13.04,硬件：CubieBoard

安装：apt-get install sysbench     

1、CPU性能

oot@ubuntu:~# sysbench --test=cpu --cpu-max-prime=2000 run

sysbench 0.4.12:  multi-threaded system evaluation benchmark

Running the test with following options:

Number of threads: 1

Doing CPU performance benchmark

Threads started!

Done.

Maximum prime number checked in CPU test: 2000

Test execution summary:

    total time:                          30.4792s

    total number of events:              10000

    total time taken by event execution: 30.4569

    per-request statistics:

         min:                                  2.81ms

         avg:                                  3.05ms

         max:                                 68.14ms

         approx.  95 percentile:               2.85ms

Threads fairness:

    events (avg/stddev):           10000.0000/0.00

    execution time (avg/stddev):   30.4569/0.00

2、多线程

root@ubuntu:~# sysbench --test=threads --num-threads=64 --thread-yields=100 --thread-locks=2 run

sysbench 0.4.12:  multi-threaded system evaluation benchmark

Running the test with following options:

Number of threads: 64

Doing thread subsystem performance test

Thread yields per test: 100 Locks used: 2

Threads started!

Done.

Test execution summary:

    total time:                          5.3406s

    total number of events:              10000

    total time taken by event execution: 335.3376

    per-request statistics:

         min:                                  0.14ms

         avg:                                 33.53ms

         max:                               2368.70ms

         approx.  95 percentile:             166.30ms

Threads fairness:

    events (avg/stddev):           156.2500/59.11

    execution time (avg/stddev):   5.2396/0.03

3、内存性能

root@ubuntu:~# sysbench --test=memory --num-threads=16 --memory-block-size=8192 --memory-total-size=1G run

sysbench 0.4.12:  multi-threaded system evaluation benchmark

Running the test with following options:

Number of threads: 16

Doing memory operations speed test

Memory block size: 8K

Memory transfer size: 1024M

Memory operations type: write

Memory scope type: global

Threads started!

Done.

Operations performed: 131072 (29189.66 ops/sec)

1024.00 MB transferred (228.04 MB/sec)

Test execution summary:

    total time:                          4.4904s

    total number of events:              131072

    total time taken by event execution: 50.0608

    per-request statistics:

         min:                                  0.01ms

         avg:                                  0.38ms

         max:                                228.90ms

         approx.  95 percentile:               0.08ms

Threads fairness:

    events (avg/stddev):           8192.0000/211.91

    execution time (avg/stddev):   3.1288/0.24

4、互斥性能

root@ubuntu:~# sysbench --test=mutex --num-threads=16 \--mutex-num=1024 --mutex-locks=10000 --mutex-loops=5000 run

sysbench 0.4.12:  multi-threaded system evaluation benchmark

Running the test with following options:

Number of threads: 16

Doing mutex performance test

Threads started!

Done.

Test execution summary:

    total time:                          1.4546s

    total number of events:              16

    total time taken by event execution: 20.3246

    per-request statistics:

         min:                               1063.12ms

         avg:                               1270.29ms

         max:                               1424.07ms

         approx.  95 percentile:            1423.61ms

Threads fairness:

    events (avg/stddev):           1.0000/0.00

    execution time (avg/stddev):   1.2703/0.12

5、文件I/O

    5.1、测试文件准备：

root@ubuntu:/mnt/sata# sysbench --test=fileio --num-threads=16 --file-total-size=300M --file-test-mode=rndrw prepare

sysbench 0.4.12:  multi-threaded system evaluation benchmark

128 files, 2400Kb each, 300Mb total

Creating files for the test...

    5.2、测试：

root@ubuntu:/mnt/sata# sysbench --test=fileio --num-threads=16 --file-total-size=300M --file-test-mode=rndrw run

sysbench 0.4.12:  multi-threaded system evaluation benchmark

Running the test with following options:

Number of threads: 16

Extra file open flags: 0

128 files, 2.3438Mb each

300Mb total file size

Block size 16Kb

Number of random requests for random IO: 10000

Read/Write ratio for combined random IO test: 1.50

Periodic FSYNC enabled, calling fsync() each 100 requests.

Calling fsync() at the end of test, Enabled.

Using synchronous I/O mode

Doing random r/w test

Threads started!

Done.

Operations performed:  5996 Read, 4004 Write, 8960 Other = 18960 Total

Read 93.688Mb  Written 62.562Mb  Total transferred 156.25Mb  (3.6605Mb/sec)

  234.27 Requests/sec executed

Test execution summary:

    total time:                          42.6858s

    total number of events:              10000

    total time taken by event execution: 62.8871

    per-request statistics:

         min:                                  0.38ms

         avg:                                  6.29ms

         max:                                386.69ms

         approx.  95 percentile:              45.88ms

Threads fairness:

    events (avg/stddev):           625.0000/62.41

    execution time (avg/stddev):   3.9304/0.37

    5.3、清理测试文件：

root@ubuntu:/mnt/sata# sysbench --test=fileio --num-threads=16 --file-total-size=300M --file-test-mode=rndrw cleanup

sysbench 0.4.12:  multi-threaded system evaluation benchmark

Removing test files...