[ale] A little math

Dennis Ruzeski denniruz at gmail.com
Wed Feb 10 13:00:25 EST 2010


I did this with a hardware random number generator and a 300g hard
drive in under 6 hours.

-Dennis

On Wed, Feb 10, 2010 at 12:53 PM, Scott Castaline <skotchman at gmail.com> wrote:
> On 02/10/2010 12:14 PM, Sean McNealy wrote:
>> Testing to a file on my machine (no raid going on)
>> 512000000 bytes (512 MB) copied, 81.1661 s, 6.3 MB/s
>>
>> extrapolation: 1TB @ 6.3 MB/s is 44 hours.  Wow, that is a long time.
>>
>> I forget the relevant specs for this machine, but for comparison
>> copying that same 512MB file was:
>> 512000000 bytes (512 MB) copied, 7.091 s, 72.2 MB/s
>>
>> And... now I'm out of entropy!
>>
>> -Sean
>>
>> On Wed, Feb 10, 2010 at 11:35 AM, Scott Castaline<skotchman at gmail.com>  wrote:
>>> Okay I've got a dumb question for you math types. How long should it
>>> take to fill a 1TB hdd with random data using
>>> "dd if=/dev/urandom of=/dev/sd"? I've done some more searching and found
>>> some numbers and if I figured them right I'm looking at about 8 days. Is
>>> this accurate?
>>> _______________________________________________
>>> Ale mailing list
>>> Ale at ale.org
>>> http://mail.ale.org/mailman/listinfo/ale
>>> See JOBS, ANNOUNCE and SCHOOLS lists at
>>> http://mail.ale.org/mailman/listinfo
>>>
>> _______________________________________________
>> Ale mailing list
>> Ale at ale.org
>> http://mail.ale.org/mailman/listinfo/ale
>> See JOBS, ANNOUNCE and SCHOOLS lists at
>> http://mail.ale.org/mailman/listinfo
>>
> But don't you have to figure in creating the random data? This would
> affect the throughput to the hdd, wouldn't it? My system has AMD dual
> core ~ 2.6GHz with 4GB 800MHz RAM, so my time would be a little faster
> than someone with a single core say 2.0GHz and 2GB RAM. I'm not sure how
> much of an impact.
>
> Anyway, I'm trying to figure out if I should just let it run its course
> or kill it now. Originally I had created the LVM stuff and did a ext4
> format with badblock -c -c which does a destructive write and read of 4
> data patterns which took ~ 23Hrs, so I may have foolishly thought that
> it would take less time to do this. Now I'm finding that thought was way
> out in left field. If I choose to terminate will that hurt anything or
> just leave a partially filled drive with random data?
> _______________________________________________
> Ale mailing list
> Ale at ale.org
> http://mail.ale.org/mailman/listinfo/ale
> See JOBS, ANNOUNCE and SCHOOLS lists at
> http://mail.ale.org/mailman/listinfo
>



More information about the Ale mailing list