[prev in list] [next in list] [prev in thread] [next in thread] 

List:       linaro-flashbench-results
Subject:    [Flashbench] Lexar JumpDrive TwistTurn 4GB USB flashdrive
From:       arnd () arndb ! de (Arnd Bergmann)
Date:       2011-07-28 22:12:41
Message-ID: 2200699.jxgqG7pa4V () wuerfel
[Download RAW message or body]

On Thursday 28 July 2011 14:46:34 Ajax Criterion wrote:
> 
> bash-4.1# flashbench --findfat --fat-nr=15 --erasesize=$[1* 1024*1024]
> --random --blocksize=512 /dev/sdc
> 1MiB    3.04M/s  7.38M/s  3.06M/s  3.06M/s  3.06M/s  3.07M/s  3.05M/s 7.47M/s  \
> 7.46M/s  7.45M/s  7.42M/s  7.39M/s  7.39M/s  7.35M/s  7.46M/s 512KiB  7.09M/s  \
> 7.24M/s  3.04M/s  3.05M/s  3.07M/s  3.04M/s  2.41M/s 2.43M/s  2.42M/s  2.44M/s  \
> 3.16M/s  3.18M/s  3.18M/s  3.16M/s  3.16M/s 256KiB  3.01M/s  4.28M/s  4.27M/s  \
> 4.28M/s  4.28M/s  3.01M/s  2.39M/s 2.4M/s   2.41M/s  2.42M/s  2.4M/s   2.4M/s   \
> 2.4M/s   2.42M/s  2.41M/s 128KiB  6.76M/s  2.98M/s  3M/s     2.99M/s  2.97M/s  \
> 2.97M/s  2.98M/s 1.87M/s  3M/s     2.98M/s  2.99M/s  2.99M/s  2.99M/s  2.97M/s  \
> 2.99M/s 64KiB   2.98M/s  3M/s     2.98M/s  2.98M/s  2.99M/s  3M/s     2.19M/s \
> 2.19M/s  2.18M/s  2.19M/s  2.19M/s  2.19M/s  2.2M/s   2.2M/s   2.19M/s 32KiB   \
> 2.82M/s  2.84M/s  2.84M/s  2.83M/s  2.83M/s  2.82M/s  2.83M/s 2.86M/s  2.83M/s  \
> 2.83M/s  2.85M/s  2.84M/s  2.84M/s  2.84M/s  2.84M/s 16KiB   5.14M/s  2.61M/s  \
> 2.6M/s   2.62M/s  2.61M/s  2.62M/s  2.62M/s 2.61M/s  2.61M/s  2.62M/s  2.61M/s  \
> 2.6M/s   2.6M/s   2.61M/s  2.63M/s 8KiB    2.24M/s  1.56M/s  2.26M/s  2.25M/s  \
> 2.25M/s  2.25M/s  2.23M/s 2.24M/s  2.25M/s  2.23M/s  2.24M/s  2.25M/s  1.34M/s  \
> 1.34M/s  1.34M/s 4KiB    1.04M/s  1.05M/s  1.05M/s  1.05M/s  1.05M/s  1.05M/s  \
> 919K/s  779K/s   783K/s   785K/s   787K/s   784K/s   784K/s   785K/s   783K/s 2KiB  \
> 507K/s   464K/s   507K/s   508K/s   507K/s   508K/s   466K/s  430K/s   429K/s   \
> 428K/s   427K/s   429K/s   429K/s   429K/s   429K/s ^C
> bash-4.1# ^C
> bash-4.1#
> 
> Strange....still a lot of variation going on.  I'll leave the final
> analysis up to you...obviously 

I have no idea either. My guess is that it doesn't actually do anything
special here, and all we see are side-effects of the way we measure.

	Arnd


[prev in list] [next in list] [prev in thread] [next in thread]