全志H2+与G3260sysbench

先看看单核的


root@zc-G3260-desktop:/home/zc# sysbench --num-threads=1 --test=cpu --cpu-max-prime=20000 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: 20000


Test execution summary:
    total time:                          24.3450s
    total number of events:              10000
    total time taken by event execution: 24.3437
    per-request statistics:
         min:                                  2.42ms
         avg:                                  2.43ms
         max:                                  3.67ms
         approx.  95 percentile:               2.45ms

Threads fairness:
    events (avg/stddev):           10000.0000/0.00
    execution time (avg/stddev):   24.3437/0.00

root@zc-G3260-desktop:/home/zc# sysbench --num-threads=1 --test=cpu --cpu-max-prime=20000 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: 20000


Test execution summary:
    total time:                          24.3284s
    total number of events:              10000
    total time taken by event execution: 24.3272
    per-request statistics:
         min:                                  2.42ms
         avg:                                  2.43ms
         max:                                  4.78ms
         approx.  95 percentile:               2.45ms

Threads fairness:
    events (avg/stddev):           10000.0000/0.00
    execution time (avg/stddev):   24.3272/0.00

root@zc-G3260-desktop:/home/zc#




root@orange-pi-zero:/home/zc# sysbench --num-threads=1 --test=cpu --cpu-max-prime=20000 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: 20000


Test execution summary:
    total time:                          1169.7694s
    total number of events:              10000
    total time taken by event execution: 1169.7518
    per-request statistics:
         min:                                116.91ms
         avg:                                116.98ms
         max:                                127.97ms
         approx.  95 percentile:             117.06ms

Threads fairness:
    events (avg/stddev):           10000.0000/0.00
    execution time (avg/stddev):   1169.7518/0.00

root@orange-pi-zero:/home/zc# sysbench --num-threads=1 --test=cpu --cpu-max-prime=20000 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: 20000


Test execution summary:
    total time:                          1169.7820s
    total number of events:              10000
    total time taken by event execution: 1169.7648
    per-request statistics:
         min:                                116.92ms
         avg:                                116.98ms
         max:                                120.09ms
         approx.  95 percentile:             117.09ms

Threads fairness:
    events (avg/stddev):           10000.0000/0.00
    execution time (avg/stddev):   1169.7648/0.00

root@orange-pi-zero:/home/zc#

基本上没啥好说的,50倍左右的差异
而直观感受是一个需要24秒,一个需要20分钟
-----------------
全核心PK



root@zc-G3260-desktop:/home/zc# sysbench --num-threads=2 --test=cpu --cpu-max-prime=20000 run
sysbench 0.4.12:  multi-threaded system evaluation benchmark

Running the test with following options:
Number of threads: 2

Doing CPU performance benchmark

Threads started!
Done.

Maximum prime number checked in CPU test: 20000


Test execution summary:
    total time:                          12.4594s
    total number of events:              10000
    total time taken by event execution: 24.9102
    per-request statistics:
         min:                                  2.42ms
         avg:                                  2.49ms
         max:                                 34.78ms
         approx.  95 percentile:               2.64ms

Threads fairness:
    events (avg/stddev):           5000.0000/87.00
    execution time (avg/stddev):   12.4551/0.00

root@zc-G3260-desktop:/home/zc#


root@orange-pi-zero:/home/zc# sysbench --num-threads=4 --test=cpu --cpu-max-prime=20000 run
sysbench 0.4.12:  multi-threaded system evaluation benchmark

Running the test with following options:
Number of threads: 4

Doing CPU performance benchmark

Threads started!
Done.

Maximum prime number checked in CPU test: 20000


Test execution summary:
    total time:                          292.4553s
    total number of events:              10000
    total time taken by event execution: 1169.6772
    per-request statistics:
         min:                                116.86ms
         avg:                                116.97ms
         max:                                156.95ms
         approx.  95 percentile:             117.09ms

Threads fairness:
    events (avg/stddev):           2500.0000/1.00
    execution time (avg/stddev):   292.4193/0.03

root@orange-pi-zero:/home/zc# sysbench --num-threads=4 --test=cpu --cpu-max-prime=20000 run
sysbench 0.4.12:  multi-threaded system evaluation benchmark

Running the test with following options:
Number of threads: 4

Doing CPU performance benchmark

Threads started!
Done.

Maximum prime number checked in CPU test: 20000


Test execution summary:
    total time:                          292.4229s
    total number of events:              10000
    total time taken by event execution: 1169.6353
    per-request statistics:
         min:                                116.86ms
         avg:                                116.96ms
         max:                                156.84ms
         approx.  95 percentile:             117.13ms

Threads fairness:
    events (avg/stddev):           2500.0000/1.22
    execution time (avg/stddev):   292.4088/0.01

root@orange-pi-zero:/home/zc#

也是一样的


-------------
而树没拍3呢..
看网上的测评 单核心在480 左右 4核心在120左右
基本上2倍2H+的水平


G3260用的是普通ubuntu16.04
h2+ 是armbian ubuntu 16.04 4.11的内核






----------------------------armbian3.56 4.13的内核貌似高了一些了 比原来基本上翻翻了

 :~$ sysbench --num-threads=1 --test=cpu --cpu-max-prime=20000 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: 20000


Test execution summary:
    total time:                          470.5259s
    total number of events:              10000
    total time taken by event execution: 470.5166
    per-request statistics:
         min:                                 46.75ms
         avg:                                 47.05ms
         max:                                237.48ms
         approx.  95 percentile:              46.89ms

Threads fairness:
    events (avg/stddev):           10000.0000/0.00
    execution time (avg/stddev):   470.5166/0.00


-----------------------------------
最近我又TB 了一个S905X的 mxq pro+盒子,刷了armbian 64位的 跑单核 成绩 31左右 4核 7左右