[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 #16 from deJong <hellrider8881 at yahoo.com> ---
I have tested the patch set and unfortunately it made no difference

root at testbsd11:~ # sysctl kern.timecounter.choice
kern.timecounter.choice: TSC-low(-100) i8254(0) ACPI-fast(900) HPET(950)
dummy(-1000000)

root at testbsd11:~ # sysbench --num-threads=1 --test=memory
--memory-total-size=1G --memory-block-size=1K 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: 1024M

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

Operations performed: 1048576 (34976.80 ops/sec)

1024.00 MB transferred (34.16 MB/sec)


Test execution summary:
    total time:                          29.9792s
    total number of events:              1048576
    total time taken by event execution: 21.9685
    per-request statistics:
         min:                                  0.02ms
         avg:                                  0.02ms
         max:                                 22.21ms
         approx.  95 percentile:               0.01ms

Threads fairness:
    events (avg/stddev):           1048576.0000/0.00
    execution time (avg/stddev):   21.9685/0.00

So either the problem is somewhere else or these patches does not apply to this
situation, it would be good if someone can confirm or deny this.

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