Mirror/zeek
1
0
Fork 0
mirror of https://github.com/zeek/zeek.git synced 2025-10-02 14:48:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

Change Hashing from H3 to Siphash.

Browse source 
This commit mostly changes the hash function that is used for Internal
hashing of data < 36 bytes from H3 to Siphash. This change is motivated
by the fact that it turns out that H3 apparently does not deliver a very
good source of data uniqueness; running HLL with H3 as a hashing
function results in quite poor results (up to of 75% off in my tests).
In difference, running HLL with Siphash (or HMAC-MD5) changes this
factor to ~2%.

This also fixes a long-standing bug in Hash.h which truncated our hash
values to 32 bit on most machines.

Furthermore, it once again fixes a problem with the Rank function in
HLL.
This commit is contained in:
Johanna Amann 2016-07-13 06:35:32 -07:00
parent c15f48661d
commit e1218cc7fa
10 changed files with 257 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

17
src/Hash.cc
View file

@ -19,14 +19,15 @@
#include "Hash.h"
#include "H3.h"
const H3<hash_t, UHASH_KEY_SIZE>* h3;
extern "C" {
extern int siphash( uint8_t *out, const uint8_t *in, uint64_t inlen, const uint8_t *k );
}
void init_hash_function()
{
// Make sure we have already called init_random_seed().
ASSERT(hmac_key_set);
h3 = new H3<hash_t, UHASH_KEY_SIZE>();
assert(hmac_key_set);
assert(siphash_key_set);
}
HashKey::HashKey(bro_int_t i)
@ -164,14 +165,16 @@ void* HashKey::CopyKey(const void* k, int s) const
hash_t HashKey::HashBytes(const void* bytes, int size)
{
assert(sizeof(hash_t) == 8);
hash_t digest[2]; // 2x hash_t (uint64) = 128 bits = 32 hex chars = sizeof md5
if ( size <= UHASH_KEY_SIZE )
{
// H3 doesn't check if size is zero
return ( size == 0 ) ? 0 : (*h3)(bytes, size);
siphash((uint8_t*)digest, (const uint8_t*)bytes, size, shared_siphash_key);
return digest[0];
}
// Fall back to HMAC/MD5 for longer data (which is usually rare).
hash_t digest[16];
hmac_md5(size, (const unsigned char*) bytes, (unsigned char*) digest);
return digest[0];
}