Re: Which SATA Combos To Consider?

["Johny Ågotnes" <johny@agotnes.com>]

Had a look at the libata docco and the driver, and don't worry about 
answering my question on the onboard RAM, I see that information gets 
copied;

DMA -> DIMM -> Drive
Drive -> DIMM -> DMA

So the memory is rather crucial in this matter.

I'll need to investigate all 1468 lines of code in sata_sx4.c in more 
detail to figure out what is going on further. If nothing else I'll 
submit some docco gumpf on the structure of the driver as I figure it 
out myself, will be done as a patch to the libata docco.

:)J

Johny Ågotnes wrote:
> Jeff,
> 
> I swapped cables and tried 3 different RAM chips, so yep, did that :) 
> Question on that - does the RAM 'matter' as the driver doesn't use it? 
> I.e. is it used by the onboard control logic as cache?
> 
> Also tried moving the card to different PCI slots, still no luck :(
> 
> Now that server is my home server running off PATA drives, the SX4 card 
> is sitting gathering dust (as I said) until I get my old PC operational 
> again and can put the card in to re-test.
> 
> A few people seem to have this problem, so it is definitely worthwhile 
> having a look at, I'd love to have a go just out of my own curiousity. 
> Closest I've been to this kinda programming is interfacing with 
> telephone switches for softphone and ACD functionality, I'm hoping 
> that'll help me get a grasp in the interrupt driven space of hardware! :)
> 
> All I need is a bit of time ;)
> 
> :)J
> 
> Jeff Garzik wrote:
> 
>> On Fri, Feb 18, 2005 at 10:44:57AM +1000, Johny Ågotnes wrote:
>>
>>> Just a quick note on the SX4 Card - I have seen data corruption on 
>>> hard-drives too in the simplest possible setup, so I'd stay clear of 
>>> that card until further notice.
>>>
>>> Mine is sitting in a cupboard right now, awaiting 'someone' (me, if I 
>>> get some time to learn low-level kernel drivers) debugging the issue.
>>>
>>> Basically, accessing two drives via this card causes corruption, I 
>>> had it working ok when I only accessed 1 drive, which is kinda 
>>> pointless...
>>
>>
>>
>> I've not need about to reproduce this in the lab.
>>
>> Have you tried switching out RAM and cables?
>>
>>     Jeff
>>
>>
>>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-ide" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html