[Bug 216759] [kern] Memory speed with small blocks (1K) up to 35 times slower than host system (under QEMU emulation, but not only)

[bugzilla-noreply at freebsd.org]

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=216759

--- Comment #6 from Roger Pau Monné <royger at freebsd.org> ---
This are the results of the tests on bare-metal using FreeBSD 12 (less than 1
month old):

# sysbench --num-threads=1 --test=memory --memory-total-size=4G 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: 4096M

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

Operations performed: 4194304 (1122695.18 ops/sec)

4096.00 MB transferred (1096.38 MB/sec)


Test execution summary:
    total time:                          3.7359s
    total number of events:              4194304
    total time taken by event execution: 2.6089
    per-request statistics:
         min:                                  0.00ms
         avg:                                  0.00ms
         max:                                  0.22ms
         approx.  95 percentile:               0.00ms

Threads fairness:
    events (avg/stddev):           4194304.0000/0.00
    execution time (avg/stddev):   2.6089/0.00

# sysbench --num-threads=1 --test=memory --memory-total-size=4G
--memory-block-size=1M 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: 1024K

Memory transfer size: 4096M

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

Operations performed: 4096 (10462.26 ops/sec)

4096.00 MB transferred (10462.26 MB/sec)


Test execution summary:
    total time:                          0.3915s
    total number of events:              4096
    total time taken by event execution: 0.3898
    per-request statistics:
         min:                                  0.06ms
         avg:                                  0.10ms
         max:                                  0.17ms
         approx.  95 percentile:               0.10ms

Threads fairness:
    events (avg/stddev):           4096.0000/0.00
    execution time (avg/stddev):   0.3898/0.00

-- 
You are receiving this mail because:
You are the assignee for the bug.