eli Posted December 23, 2016 Posted December 23, 2016 Hello all, iv'e made some sysbench tests on Pine64, Orange Pi PC2 and Raspberry Pi 3. all three boards are running on aarch64 based OS, for the Pine64 I used Armbian Ubuntu Xenial Server, for the Orange Pi PC2 I used the latest ubuntu image provided by Xunlong and for the Raspberry Pi 3 I used fedora 24 image provided by kraxel the boards: http://s.pictub.club/2016/12/23/sDJQCq.jpg Raspberry Pi 3: [eli@fedora-rpi2 ~]$ uname -a Linux fedora-rpi2 4.9.0-1-main #1 SMP PREEMPT Mon Dec 12 09:14:22 UTC 2016 aarch64 aarch64 aarch64 GNU/Linux [eli@fedora-rpi2 ~]$ for each in 1 2 4; do sysbench --test=cpu --cpu-max-prime=20000 --num-threads=$each run; done 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! WARNING: Operation time (18446744073215141888.000000) is greater than maximal counted value, counting as 10000000000000.000000 WARNING: Percentile statistics will be inaccurate Done. Maximum prime number checked in CPU test: 20000 Test execution summary: total time: 60.6489s total number of events: 10000 total time taken by event execution: 60.6428 per-request statistics: min: 6.03ms avg: 6.06ms max: 18446744073215.31ms approx. 95 percentile: 6.05ms Threads fairness: events (avg/stddev): 10000.0000/0.00 execution time (avg/stddev): 60.6428/0.00 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: 29.9795s total number of events: 10000 total time taken by event execution: 59.9449 per-request statistics: min: 5.84ms avg: 5.99ms max: 6.21ms approx. 95 percentile: 6.04ms Threads fairness: events (avg/stddev): 5000.0000/0.00 execution time (avg/stddev): 29.9724/0.00 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! WARNING: Operation time (18446744073214261248.000000) is greater than maximal counted value, counting as 10000000000000.000000 WARNING: Percentile statistics will be inaccurate Done. Maximum prime number checked in CPU test: 20000 Test execution summary: total time: 16.1915s total number of events: 10000 total time taken by event execution: 64.7387 per-request statistics: min: 6.02ms avg: 6.47ms max: 18446744073219.71ms approx. 95 percentile: 6.83ms Threads fairness: events (avg/stddev): 2500.0000/105.87 execution time (avg/stddev): 16.1847/0.00 [eli@fedora-rpi2 ~]$ sysbench --test=memory --memory-block-size=1K --memory-scope=global --memory-total-size=10G --memory-oper=read run sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 1 Doing memory operations speed test Memory block size: 1K Memory transfer size: 10240M Memory operations type: read Memory scope type: global Threads started! Done. Operations performed: 10485760 (531318.94 ops/sec) 10240.00 MB transferred (518.87 MB/sec) Test execution summary: total time: 19.7353s total number of events: 10485760 total time taken by event execution: 13.8417 per-request statistics: min: 0.00ms avg: 0.00ms max: 0.07ms approx. 95 percentile: 0.00ms Threads fairness: events (avg/stddev): 10485760.0000/0.00 execution time (avg/stddev): 13.8417/0.00 [eli@fedora-rpi2 ~]$ sysbench --test=memory --memory-block-size=1K --memory-scope=global --memory-total-size=10G --memory-oper=write run sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 1 Doing memory operations speed test Memory block size: 1K Memory transfer size: 10240M Memory operations type: write Memory scope type: global Threads started! Done. Operations performed: 10485760 (364193.47 ops/sec) 10240.00 MB transferred (355.66 MB/sec) Test execution summary: total time: 28.7917s total number of events: 10485760 total time taken by event execution: 22.9432 per-request statistics: min: 0.00ms avg: 0.00ms max: 0.18ms approx. 95 percentile: 0.00ms Threads fairness: events (avg/stddev): 10485760.0000/0.00 execution time (avg/stddev): 22.9432/0.00 Orange Pi PC2: eli@Orangepi:~$ uname -a Linux Orangepi 3.10.65 #55 SMP PREEMPT Fri Nov 18 16:17:28 CST 2016 aarch64 aarch64 aarch64 GNU/Linux eli@Orangepi:~$ for each in 1 2 4; do sysbench --test=cpu --cpu-max-prime=20000 --num-threads=$each run; done sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 1 Doing CPU performance benchmark Threads started! Done. Maximum prime number checked in CPU test: 20000 Test execution summary: total time: 36.7932s total number of events: 10000 total time taken by event execution: 36.7893 per-request statistics: min: 3.62ms avg: 3.68ms max: 505.97ms approx. 95 percentile: 3.64ms Threads fairness: events (avg/stddev): 10000.0000/0.00 execution time (avg/stddev): 36.7893/0.00 sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 2 Doing CPU performance benchmark Threads started! Done. Maximum prime number checked in CPU test: 20000 Test execution summary: total time: 17.9530s total number of events: 10000 total time taken by event execution: 35.8999 per-request statistics: min: 3.51ms avg: 3.59ms max: 4.20ms approx. 95 percentile: 3.64ms Threads fairness: events (avg/stddev): 5000.0000/0.00 execution time (avg/stddev): 17.9500/0.00 sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 4 Doing CPU performance benchmark Threads started! Done. Maximum prime number checked in CPU test: 20000 Test execution summary: total time: 9.0700s total number of events: 10000 total time taken by event execution: 36.2609 per-request statistics: min: 3.60ms avg: 3.63ms max: 13.77ms approx. 95 percentile: 3.64ms Threads fairness: events (avg/stddev): 2500.0000/3.54 execution time (avg/stddev): 9.0652/0.00 eli@Orangepi:~$ sysbench --test=memory --memory-block-size=1K --memory-scope=global --memory-total-size=10G --memory-oper=read run sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 1 Doing memory operations speed test Memory block size: 1K Memory transfer size: 10240M Memory operations type: read Memory scope type: global Threads started! Done. Operations performed: 10485760 (922210.22 ops/sec) 10240.00 MB transferred (900.60 MB/sec) Test execution summary: total time: 11.3702s total number of events: 10485760 total time taken by event execution: 8.0777 per-request statistics: min: 0.00ms avg: 0.00ms max: 0.39ms approx. 95 percentile: 0.00ms Threads fairness: events (avg/stddev): 10485760.0000/0.00 execution time (avg/stddev): 8.0777/0.00 eli@Orangepi:~$ sysbench --test=memory --memory-block-size=1K --memory-scope=global --memory-total-size=10G --memory-oper=write run sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 1 Doing memory operations speed test Memory block size: 1K Memory transfer size: 10240M Memory operations type: write Memory scope type: global Threads started! Done. Operations performed: 10485760 (617633.57 ops/sec) 10240.00 MB transferred (603.16 MB/sec) Test execution summary: total time: 16.9773s total number of events: 10485760 total time taken by event execution: 13.6888 per-request statistics: min: 0.00ms avg: 0.00ms max: 0.32ms approx. 95 percentile: 0.00ms Threads fairness: events (avg/stddev): 10485760.0000/0.00 execution time (avg/stddev): 13.6888/0.00 Pine64: eli@pine64:~$ uname -a Linux pine64 3.10.102-pine64 #6 SMP PREEMPT Thu Sep 15 09:11:23 CEST 2016 aarch64 aarch64 aarch64 GNU/Linux eli@pine64:~$ for each in 1 2 4; do sysbench --test=cpu --cpu-max-prime=20000 --num-threads=$each run; done sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 1 Doing CPU performance benchmark Threads started! Done. Maximum prime number checked in CPU test: 20000 Test execution summary: total time: 31.7566s total number of events: 10000 total time taken by event execution: 31.7533 per-request statistics: min: 3.17ms avg: 3.18ms max: 3.54ms approx. 95 percentile: 3.18ms Threads fairness: events (avg/stddev): 10000.0000/0.00 execution time (avg/stddev): 31.7533/0.00 sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 2 Doing CPU performance benchmark Threads started! Done. Maximum prime number checked in CPU test: 20000 Test execution summary: total time: 15.8911s total number of events: 10000 total time taken by event execution: 31.7757 per-request statistics: min: 3.17ms avg: 3.18ms max: 3.74ms approx. 95 percentile: 3.19ms Threads fairness: events (avg/stddev): 5000.0000/4.00 execution time (avg/stddev): 15.8878/0.00 sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 4 Doing CPU performance benchmark Threads started! Done. Maximum prime number checked in CPU test: 20000 Test execution summary: total time: 7.9636s total number of events: 10000 total time taken by event execution: 31.8266 per-request statistics: min: 3.17ms avg: 3.18ms max: 13.22ms approx. 95 percentile: 3.19ms Threads fairness: events (avg/stddev): 2500.0000/4.95 execution time (avg/stddev): 7.9567/0.00 eli@pine64:~$ sysbench --test=memory --memory-block-size=1K --memory-scope=global --memory-total-size=10G --memory-oper=read run sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 1 Doing memory operations speed test Memory block size: 1K Memory transfer size: 10240M Memory operations type: read Memory scope type: global Threads started! Done. Operations performed: 10485760 (1052151.29 ops/sec) 10240.00 MB transferred (1027.49 MB/sec) Test execution summary: total time: 9.9660s total number of events: 10485760 total time taken by event execution: 7.0809 per-request statistics: min: 0.00ms avg: 0.00ms max: 0.37ms approx. 95 percentile: 0.00ms Threads fairness: events (avg/stddev): 10485760.0000/0.00 execution time (avg/stddev): 7.0809/0.00 eli@pine64:~$ sysbench --test=memory --memory-block-size=1K --memory-scope=global --memory-total-size=10G --memory-oper=write run sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 1 Doing memory operations speed test Memory block size: 1K Memory transfer size: 10240M Memory operations type: write Memory scope type: global Threads started! Done. Operations performed: 10485760 (704345.05 ops/sec) 10240.00 MB transferred (687.84 MB/sec) Test execution summary: total time: 14.8872s total number of events: 10485760 total time taken by event execution: 12.0413 per-request statistics: min: 0.00ms avg: 0.00ms max: 0.15ms approx. 95 percentile: 0.00ms Threads fairness: events (avg/stddev): 10485760.0000/0.00 execution time (avg/stddev): 12.0413/0.00
tkaiser Posted December 23, 2016 Posted December 23, 2016 Unfortunately these are numbers without meaning. Sysbench can be used to heat chips but not to measure performance of different hardware, especially not in your mode. Details: https://forum.armbian.com/index.php/topic/1748-sbc-consumptionperformance-comparisons/ It should also be noted that potential throttling has to be monitored, that OPi PC 2 with the crappy BSP based OS image you used is limited to 1008 MHz and that RPi is cheating on you since cpufreq sysfs nodes lie (they report 1200 MHz even when the CPU cores run only with 800 MHz) CPU wise A64 and H5 should perform identical and RPi when using ARMv8 code should be slightly faster. Apart from that it's all about settings and use cases so these passive benchmarking approaches producing some numbers are always useless anyway 1
Recommended Posts