First of all: Thanks for the great work on btrfs! How about taking only few bytes of data from each block and compare those, before attempting to hash? This way you could quickly discard blocks with really no similar data and hash only ones that matched the "first look" byte comparison? This could lead to less CPU consumption, since hashing is an intense operation, and to less memory footprint, since you don't need to store all those non-dedupable hashes. -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
