Is my data checksummed?

[Ric Wheeler]

On 02/23/2010 04:56 AM, Reza Roboubi wrote:
> Thanks a lot for all the responses.
>
> Ric Wheeler wrote:
>> On 02/21/2010 09:41 PM, tytso at mit.edu wrote:
>>> If you use disks that support the Data Integrity Field (DIF)
>>> extension, Linux will use it to provide end-to-end data checksum
>>> support. Otherwise, there are checksums on the disk and between disk
>>> controller and the CPU, but those are obviously not end-to-end
>>> checksums.
>>
>> Just to be clear, even with a storage path that supports DIF/DIX, we
>> don't currently do anything for applications on top of file systems.
>> The primary application to target storage path is covered mainly for
>> raw devices.
>
> Sorry Ric,
>
> The last sentence loses me. I mean, I know what raw devices are! :)
> Would you please elaborate a little.
>
> Reza.

Sorry for the confusion. It confuses me now that I try to reread it as well :-(

What I was trying to say is that in this first implementation, the only 
applications that can take advantage of DIF/DIX extra data protection will need 
to do it all themselves and will need to use raw devices (no file systems).

Oracle's DB will be a likely candidate as will a very few other sophisticated 
applications.

Note that the other mode of operation (HBA -> target storage device) is 
invisible and will work for everyone. It just does not protect against data 
corruption higher in the stack (above the HBA/device driver).

ric