Two things:
1) On output you only get checksumming if your applications
use sendfile()
2) On input, since we have to copy the data anyways, we use
csum_partial_copy because it costs the same as a memcpy.
Actually, on some x86 cpus the checksum+copy is faster
than the memcpy, but that is being fixed in current 2.5.x
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/