[Nottingham] 'Memtest86+' for HDDs and SSDs?

Martin martin at ml1.co.uk
Wed Apr 25 22:19:52 UTC 2012


On 25/04/12 21:46, Duncan wrote:
> On 24/04/12 14:23, Martin wrote:
[---]
>>
>> Before I embark on the next batch of ad-hocness, I was wondering if
>> anyone had put together something for some more refined/thorough testing...
>>
> 
> An additional tool for your arsenal:
> If the disk has SMART (many SATA, SAS and SCSI these days do) then you can use smartmontools
> to initiate disk self-tests (offline, short and long).  If your lucky SMART has already been enabled
> and you can use smartmontools to see what it says.
> See also http://smartmontools.sourceforge.net/badblockhowto.html
> 
> NB. "smartctl long" (and full badblocks) tests of large disks can take a very long time and your
> HDD will get very hot in the process if your box doesn't have adequate ventilation.

Thanks for the smartmontools and good points.

The "will get very hot in the process" is part of the test! Something
that badblocks doesn't really exercise. Hence the question...


Thinking further, is there something like Bonnie but that also verifies
the results rather than merely gathering timings?...

Or do people just assume blindly that their disk drives just simply
work, flawlessly?

(Or am I the only one to have had new HDDs "doa" or soon-to-die?)


Cheers,
Martin


Bonnie
http://www.coker.com.au/bonnie++/


-- 
- ------------------ - ----------------------------------------
-    Martin Lomas    - OpenPGP (GPG/PGP) Public Key: 0xCEE1D3B7
- martin @ ml1 co uk - Import from   hkp://subkeys.pgp.net   or
- ------------------ - http:// ml1 .co .uk/martin_ml1_co_uk.gpg



More information about the Nottingham mailing list