Mike Christie wrote:
I am not sure if the first mail got sent out. Here is the correct mail with the patch. Hey Lars, Here is what I meant. A Page for just something around 8-16 bytes seems wasteful. Plus there is no reserve. If you have to end up setting more bits maybe it is better to preallocate a command per device at create time, or maybe since there are four different combos I should have done it with this patch? This was made against 2.6.12-rc2. Only compile tested. Mike
+ if (bio_add_page(bio, virt_to_page(data), data_size, + offset_in_page(data)) != data_size) {
My concern though is that I do no think I can do this. I mean we cannot start the IO from the middle of a page.