Chris,<br><br>Thanks for the actual numbers in your post. On what CPU did you pull these numbers? <br><br>Also, I think your calculations are wrong for overwriting a 300GB drive. We routinely write 1TB+ to drives and I have a chart of transfer rates for our data folks.<br>
<br>1TB at 100MB/sec = 3 hours<br>1TB at 10MB/sec = 30 hours<br>1TB at 1MB/sec = 300 hours<br><br>We routinely hit 80 - 90MB/sec on 2TB HDDs, not 3MB/sec.<br><br>100MB/sec is about 1/3rd of the SATA bandwidth (I know that isn't exact but for simplicity's sake I equate 1Gb/sec to 100MB/sec). I think your SATA speed calculation should be 3*1024^3 (kilobits, megabits, gigabits). <br>
<br>Dan Kulinski<br><br><div class="gmail_quote">On Wed, Jun 1, 2011 at 10:26 AM, chris fedde <span dir="ltr"><<a href="mailto:chris@fedde.us">chris@fedde.us</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
It might be a good idea to switch to /dev/zero. It is much faster<br>
than /dev/random<br>
You need to wait for it to finish to overwrite the whole disk. As a<br>
least upper bound on the run time take the disk size and divide by the<br>
advertised transfer rate of the interface. 300Gbyte = 300*1024^3,<br>
3Mbyte/sec ideal SATA speed = 3*1024^2<br>
<br>
using bc -l<br>
<br>
(300*1024^3)/(3*1024^2)<br>
102400.00000000000000000000<br>
./3600<br>
28.44444444444444444444<br>
<br>
about 29 hours if you really get full bandwidth from your sata port.<br>
Chances are that's a gross under estimate.<br>
<br>
Here is a quick device timing test:<br>
<br>
[cfedde@home]$ dd if=/dev/urandom of=/dev/null bs=4096 count=1000<br>
1000+0 records in<br>
1000+0 records out<br>
4096000 bytes (4.1 MB) copied, 0.532551 seconds, 7.7 MB/s<br>
<br>
[cfedde@home]$ dd if=/dev/zero of=/dev/null bs=4096 count=1000<br>
1000+0 records in<br>
1000+0 records out<br>
4096000 bytes (4.1 MB) copied, 0.001732 seconds, 2.4 GB/s<br>
<br>
/dev/zero is much faster than /dev/urandom<br>
<div><div></div><div class="h5"><br>
On Wed, Jun 1, 2011 at 9:07 AM, Mike Bean <<a href="mailto:beandaemon@gmail.com">beandaemon@gmail.com</a>> wrote:<br>
> No harm, no foul, it's not a particularly fast Celeron, so I don't mind<br>
> letting it run long, I just wasn't sure what to expect.<br>
><br>
> On Wed, Jun 1, 2011 at 8:15 AM, Will <<a href="mailto:will.sterling@gmail.com">will.sterling@gmail.com</a>> wrote:<br>
>><br>
>> I should have recommended /dev/zero instead of /dev/urandom. For your<br>
>> purposes it would have been just as good and faster.<br>
>><br>
>> On Wed, Jun 1, 2011 at 8:02 AM, Will <<a href="mailto:will.sterling@gmail.com">will.sterling@gmail.com</a>> wrote:<br>
>>><br>
>>> It should eventually quit on its own. The amount of time it will take is<br>
>>> dependent on how fast your CPU can generate random numbers and how large the<br>
>>> partition is.<br>
>>><br>
>>> On Wed, Jun 1, 2011 at 5:09 AM, Mike Bean <<a href="mailto:beandaemon@gmail.com">beandaemon@gmail.com</a>> wrote:<br>
>>>><br>
>>>> How long would I need to leave this running? cat /dev/urandom ><br>
>>>> /dev/sda1 's been going for long about 10 hours now. Is this something that<br>
>>>> I'll need to abort or does it terminate on its own?<br>
>>>><br>
>>>> On Tue, May 31, 2011 at 9:04 AM, chris fedde <<a href="mailto:chris@fedde.us">chris@fedde.us</a>> wrote:<br>
>>>>><br>
>>>>> Raymond,<br>
>>>>><br>
>>>>> What does the magic block size do?<br>
>>>>><br>
>>>>><br>
>>>>> I'd go with two passes of "cat /dev/urandom > /dev/sdX" as root.<br>
>>>>><br>
>>>>> On Tue, May 31, 2011 at 8:51 AM, Raymond DeRoo <<a href="mailto:rderoo@deroo.net">rderoo@deroo.net</a>><br>
>>>>> wrote:<br>
>>>>> > Mike--<br>
>>>>> ><br>
>>>>> > In short, I'm giving one of my older PC's to a friend's friend. One<br>
>>>>> > of<br>
>>>>> > those, I don't need it, things. In any case, in terms of secure<br>
>>>>> > destruction<br>
>>>>> > of drives, my father's always taught me to disassemble the drives and<br>
>>>>> > throw<br>
>>>>> > the heads and the platter out separately. Can't do it here, they<br>
>>>>> > need the<br>
>>>>> > drives, so I thought I'd ask for advice in case we have members who<br>
>>>>> > might<br>
>>>>> > know a thing or two about this sort of thing. I figured I'd probably<br>
>>>>> > just<br>
>>>>> > boot it to a live CD and nuke the partitions, and that's probably<br>
>>>>> > enough,<br>
>>>>> > after all, I don't need like a military-grade erase, but I'll settle<br>
>>>>> > for<br>
>>>>> > making it @#$@#$@$ hard to recover. Any suggestions are welcome.<br>
>>>>> ><br>
>>>>> ><br>
>>>>> > # dd if=/dev/urandom of=/dev/sda bs=387 count=<size of disk in bites><br>
>>>>> > / 383<br>
>>>>> > Recover from this *IS* still possible, but generally requires someone<br>
>>>>> > who is<br>
>>>>> > *VERY* knowledge about drives to do as such.<br>
>>>>> > .r<br>
>>>>> > _______________________________________________<br>
>>>>> > clue mailing list<br>
>>>>> > <a href="mailto:clue@cluedenver.org">clue@cluedenver.org</a><br>
>>>>> > <a href="http://cluedenver.org/mailman/listinfo/clue" target="_blank">http://cluedenver.org/mailman/listinfo/clue</a><br>
>>>>> ><br>
>>>>> _______________________________________________<br>
>>>>> clue mailing list<br>
>>>>> <a href="mailto:clue@cluedenver.org">clue@cluedenver.org</a><br>
>>>>> <a href="http://cluedenver.org/mailman/listinfo/clue" target="_blank">http://cluedenver.org/mailman/listinfo/clue</a><br>
>>>><br>
>>>><br>
>>>> _______________________________________________<br>
>>>> clue mailing list<br>
>>>> <a href="mailto:clue@cluedenver.org">clue@cluedenver.org</a><br>
>>>> <a href="http://cluedenver.org/mailman/listinfo/clue" target="_blank">http://cluedenver.org/mailman/listinfo/clue</a><br>
>>><br>
>><br>
>><br>
>> _______________________________________________<br>
>> clue mailing list<br>
>> <a href="mailto:clue@cluedenver.org">clue@cluedenver.org</a><br>
>> <a href="http://cluedenver.org/mailman/listinfo/clue" target="_blank">http://cluedenver.org/mailman/listinfo/clue</a><br>
><br>
><br>
> _______________________________________________<br>
> clue mailing list<br>
> <a href="mailto:clue@cluedenver.org">clue@cluedenver.org</a><br>
> <a href="http://cluedenver.org/mailman/listinfo/clue" target="_blank">http://cluedenver.org/mailman/listinfo/clue</a><br>
><br>
_______________________________________________<br>
clue mailing list<br>
<a href="mailto:clue@cluedenver.org">clue@cluedenver.org</a><br>
<a href="http://cluedenver.org/mailman/listinfo/clue" target="_blank">http://cluedenver.org/mailman/listinfo/clue</a><br>
</div></div></blockquote></div><br>