On Tue, 10 Sep 2013 15:37:56 +0800 Shaohua Li <shli@xxxxxxxxxx> wrote: > Below is my latest patch. > Thanks. It looks good. I have pushed it out to me for-next branch (which a few cosmetic white-space adjustments). I will need to review it again but it is certainly very close to 'right'. One thing I'm a bit concerned about is the md_raid5_congested function. It can return "false", yet a write can still block. That isn't a huge problem, but it could have some negative consequences. Maybe we could have an atomic_t which counts how many hash values as "full" and we report "congested" when any are full. Maybe. Thanks, NeilBrown
Attachment:
signature.asc
Description: PGP signature
