Raspberry Pi Benchmarks

benchmark_1.txt

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:                          94.8942s
    total number of events:              10000
    total time taken by event execution: 379.5067
    per-request statistics:
         min:                                 36.89ms
         avg:                                 37.95ms
         max:                                 73.44ms
         approx.  95 percentile:              42.62ms

Threads fairness:
    events (avg/stddev):           2500.0000/28.43
    execution time (avg/stddev):   94.8767/0.01

sysbench 0.4.12:  multi-threaded system evaluation benchmark

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

Doing memory operations speed test
Memory block size: 1K

Memory transfer size: 3072M

Memory operations type: write
Memory scope type: global
Threads started!
Done.

Operations performed: 3145728 (2023175.91 ops/sec)

3072.00 MB transferred (1975.76 MB/sec)


Test execution summary:
    total time:                          1.5548s
    total number of events:              3145728
    total time taken by event execution: 4.8555
    per-request statistics:
         min:                                  0.00ms
         avg:                                  0.00ms
         max:                                 18.31ms
         approx.  95 percentile:               0.00ms

Threads fairness:
    events (avg/stddev):           786432.0000/10216.20
    execution time (avg/stddev):   1.2139/0.01

sysbench 0.4.12:  multi-threaded system evaluation benchmark

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

Extra file open flags: 0
128 files, 3.9062Mb each
500Mb total file size
Block size 16Kb
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing sequential rewrite test
Threads started!
Done.

Operations performed:  0 Read, 32000 Write, 128 Other = 32128 Total
Read 0b  Written 500Mb  Total transferred 500Mb  (6.8221Mb/sec)
  436.62 Requests/sec executed

Test execution summary:
    total time:                          73.2907s
    total number of events:              32000
    total time taken by event execution: 253.9003
    per-request statistics:
         min:                                  0.04ms
         avg:                                  7.93ms
         max:                              11989.85ms
         approx.  95 percentile:               0.68ms

Threads fairness:
    events (avg/stddev):           8000.0000/785.51
    execution time (avg/stddev):   63.4751/0.00

benchmark_2.txt

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:                          92.8549s
    total number of events:              10000
    total time taken by event execution: 371.3566
    per-request statistics:
         min:                                 36.89ms
         avg:                                 37.14ms
         max:                                 94.87ms
         approx.  95 percentile:              37.50ms

Threads fairness:
    events (avg/stddev):           2500.0000/14.98
    execution time (avg/stddev):   92.8392/0.01

sysbench 0.4.12:  multi-threaded system evaluation benchmark

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

Doing memory operations speed test
Memory block size: 1K

Memory transfer size: 3072M

Memory operations type: write
Memory scope type: global
Threads started!
Done.

Operations performed: 3145728 (2057266.84 ops/sec)

3072.00 MB transferred (2009.05 MB/sec)


Test execution summary:
    total time:                          1.5291s
    total number of events:              3145728
    total time taken by event execution: 4.8000
    per-request statistics:
         min:                                  0.00ms
         avg:                                  0.00ms
         max:                                  4.94ms
         approx.  95 percentile:               0.00ms

Threads fairness:
    events (avg/stddev):           786432.0000/5733.96
    execution time (avg/stddev):   1.2000/0.00

sysbench 0.4.12:  multi-threaded system evaluation benchmark

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

Extra file open flags: 0
128 files, 3.9062Mb each
500Mb total file size
Block size 16Kb
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing sequential rewrite test
Threads started!
Done.

Operations performed:  0 Read, 32000 Write, 128 Other = 32128 Total
Read 0b  Written 500Mb  Total transferred 500Mb  (12.433Mb/sec)
  795.70 Requests/sec executed

Test execution summary:
    total time:                          40.2164s
    total number of events:              32000
    total time taken by event execution: 122.2957
    per-request statistics:
         min:                                  0.04ms
         avg:                                  3.82ms
         max:                               7525.67ms
         approx.  95 percentile:               0.31ms

Threads fairness:
    events (avg/stddev):           8000.0000/910.91
    execution time (avg/stddev):   30.5739/0.15

benchmarks.sh

#!/bin/bash

counter="`cat .benchmark_counter`";
echo "$((counter+1))" > .benchmark_counter;

filename="benchmark_${counter}.txt";

echo "Running benchmark, saving results to '${filename}'";

sysbench --test=cpu --cpu-max-prime=20000 --num-threads=4 run > "${filename}";
sysbench --test=memory --memory-total-size=15G --num-threads=4 run >> "${filename}";
sysbench --test=fileio --file-test-mode=seqrewr --file-total-size=500M --num-threads=4 run >> "${filename}";

cat "${filename}";