On Wed, Jun 12, 2013 at 10:40 PM, Zach Brown <zab@xxxxxxxxxx> wrote: >> I've got an alternate approach for fixing this wart in lookup_ioctx()... >> Instead of using an rbtree, just use the reserved id in the ring buffer >> header to index an array pointing the ioctx. It's not finished yet, and >> it needs to be tidied up, but is most of the way there. > > Yeah, that might work. > > Note that the patch wasn't using an rbtree, it was storing the pointer > value in a *radix* which is why single lookups took so long. Presumably > radix was used for RCU lookups. > > Your ring->id trick lets us use RCU with small ints instead of the > context pointer. It might be worth using idr instead of rolling manual > array code. It'd still be much faster than the list, but get rid of the > large alloc, array walking, memcpy(), etc. > I picked up Ben's patch and incorporated Zach's idea and the first results look promising, as expected. I am going to do a full test with the same workload I've used for rbtree and come back with the results and the patch in a day or so. Thanks everybody ! -- To unsubscribe from this list: send the line "unsubscribe linux-s390" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
