Re: conflict of interest

--MimeMultipartBoundary
Content-Type: text/plain; charset=us-ascii

 
| good idea. Just nick a byte. Someone did a paper looking at the number
| of hash collisions for md5, and even with only 8 bytes of the hash,
| the number of collisions was in the highly improbably range.

8 bytes is probably enough for almost anyone, but for alignment reasons 16 is
probably better if you want to steal the identifier byte.
|
|
| > To answer someone else's suggestion that SHA is slow - isn't SHA is
| > fast enough
| > for the Linux kernel to do on syn/recv cookies, etc? (drivers/char/random.c
| > has USE_SHA by default)
|
| I think the suggestion was slow 'compared to md5'. No idea which would
| be faster.

SHA is slower - it comes up with a 20 byte hash and has more data sloshing
around. I used the implementations from tripwire on a 50M file and came up
with the following numbers

md4 9.39s
haval 13.32s
md5 18.55s
sha 30.32s

md4 is optimised for stream digests (not all the algorithms have equal set up
times) and is known to have many more collisions than md5. md5 is known to
have collisions (ie the digest space is less than 128bits) but is certainly
adequate for this purpose. haval is like md5 but comes from a source different
to RSA.

(this was on a machine with enough ram free to have 50M in the buffer cache)

-- 
Brian Denehy,			   Internet: B-Denehy@adfa.oz.au
Information Services Division  	   MHSnet:   B-Denehy@cc.adfa.oz.au
Australian Defence Force Academy   UUCP:!uunet!munnari.oz.au!cc.adfa.oz.au!bvd
Northcott Dr. Campbell ACT Australia 2600 +61 2 6268 8141 Fax +61 2 6268 8150 
--MimeMultipartBoundary--