Cache Controller and Memory Dump

Hi,

A friend of mine told me that I need to disable the disk controller cache (backed by battery) to avoid corruption during a kernel memory dump. I know that memory dump can cause corruption (in some application structure) even without the disk controller cache, so I think that it is not necessary.

I did a little research on the web and in the DTW help and did not find anything about it. I imagine that if such situation could happen it would be very well documented.

Does anyone know if this is true?

Thanks!

-George

Unless your controller itself is broken, that sounds like it *should* be unnecessary to me. (Of course, how many RAID controllers actually provide safety with their caches is another question entirely. I’m not sure that I’d fully trust my data with the consumer-grade RAIDs shipping with desktop motherboards nowadays – but then again, those usually don’t have BBUs protecting the cache and/or logic to wait and flush the cache to disk on reset.)

  • S

-----Original Message-----
From: xxxxx@lists.osr.com [mailto:xxxxx@lists.osr.com] On Behalf Of George Luiz Bittencourt
Sent: Thursday, April 02, 2009 6:32 AM
To: Kernel Debugging Interest List
Subject: [windbg] Cache Controller and Memory Dump

Hi,

A friend of mine told me that I need to disable the disk controller cache (backed by battery) to avoid corruption during a kernel memory dump. I know that memory dump can cause corruption (in some application structure) even without the disk controller cache, so I think that it is not necessary.

I did a little research on the web and in the DTW help and did not find anything about it. I imagine that if such situation could happen it would be very well documented.

Does anyone know if this is true?

Thanks!

-George


WINDBG is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at http://www.osronline.com/page.cfm?name=ListServer