Date: Tue, 20 Dec 2016 21:29:24 -0800 From: Eric Dumazet <eric.dumazet@...il.com> To: George Spelvin <linux@...encehorizons.net> Cc: tytso@....edu, ak@...ux.intel.com, davem@...emloft.net, David.Laight@...lab.com, djb@...yp.to, ebiggers3@...il.com, hannes@...essinduktion.org, Jason@...c4.com, jeanphilippe.aumasson@...il.com, kernel-hardening@...ts.openwall.com, linux-crypto@...r.kernel.org, linux-kernel@...r.kernel.org, luto@...capital.net, netdev@...r.kernel.org, tom@...bertland.com, torvalds@...ux-foundation.org, vegard.nossum@...il.com Subject: Re: HalfSipHash Acceptable Usage On Tue, 2016-12-20 at 22:28 -0500, George Spelvin wrote: > > I do not see why SipHash, if faster than MD5 and more secure, would be a > > problem. > > Because on 32-bit x86, it's slower. > > Cycles per byte on 1024 bytes of data: > Pentium Core 2 Ivy > 4 Duo Bridge > SipHash-2-4 38.9 8.3 5.8 > HalfSipHash-2-4 12.7 4.5 3.2 > MD5 8.3 5.7 4.7 So definitely not faster. 38 cycles per byte is a problem, considering IPV6 is ramping up. But TCP session establishment on P4 is probably not a big deal. Nobody would expect a P4 to handle gazillions of TCP flows (using a 32bit kernel) What about SHA performance (syncookies) on P4 ? Synfloods are probably the only case we might take care of for 2000-era cpus.
Powered by blists - more mailing lists
Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.