On Wed, May 7, 2014 at 1:50 PM, Darrick J. Wong <[email protected]> wrote:
> Just for kicks I (sloppily) benchmarked a few of the kernel's hash
> implementations on a Core i5-3320M CPU @3.3GHz:
> xxhash: 6.0GB/s
> crc32c-intel: 11.5GB/s
> crc32c (no hw accel): 1.8GB/s

CRC also usually has the very mild data recovery advantage that if
your error is just a bitflip you can correct it using the crc in a
computationally efficient manner, potentially enabling fancy recovery
tools... so it it were merely equal in speed you'd still probably
prefer to use a CRC.
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to