memcached源码版本：memcached-1.4.24
1. 与 hash 相关的文件
- hash.h / hash.c
就一个函数 hash_init(enum hashfunc_type type) ，main函数调用，用来选择使用的 hash 函数。
hash.h
1 typedef uint32_t (*hash_func)(const void *key, size_t length); 2 hash_func hash; 3 4 enum hashfunc_type 5 { 6 JENKINS_HASH=0, 7 MURMUR3_HASH 8 }; 9 10 int hash_init(enum hashfunc_type type);
hash.c
1 #include "memcached.h" 2 #include "jenkins_hash.h" 3 #include "murmur3_hash.h" 4 5 int hash_init(enum hashfunc_type type) 6 { 7 switch(type) 8 { 9 case JENKINS_HASH: 10 hash = jenkins_hash; 11 settings.hash_algorithm = "jenkins"; 12 break; 13 case MURMUR3_HASH: 14 hash = MurmurHash3_x86_32; 15 settings.hash_algorithm = "murmur3"; 16 break; 17 default: 18 return -1; 19 } 20 return 0; 21 }
memcached提供了两种 hash 函数，分别定义在下面两个源文件中。
- jenkins_hash.h / jenkins_hash.c
jenkins_hash.h
1 uint32_t jenkins_hash(const void *key, size_t length);
jenkins_hash.c
/* -*- Mode: C; tab- 4; c-basic-offset: 4; indent-tabs-mode: nil -*- */
/*
* Hash table
*
* The hash function used here is by Bob Jenkins, 1996:
* <http://burtleburtle.net/bob/hash/doobs.html>
* "By Bob Jenkins, 1996. bob_jenkins@burtleburtle.net.
* You may use this code any way you wish, private, educational,
* or commercial. It's free."
*
*/
#include "memcached.h"
#include "jenkins_hash.h"
/*
* Since the hash function does bit manipulation, it needs to know
* whether it's big or little-endian. ENDIAN_LITTLE and ENDIAN_BIG
* are set in the configure script.
*/
#if ENDIAN_BIG == 1
# define HASH_LITTLE_ENDIAN 0
# define HASH_BIG_ENDIAN 1
#else
# if ENDIAN_LITTLE == 1
# define HASH_LITTLE_ENDIAN 1
# define HASH_BIG_ENDIAN 0
# else
# define HASH_LITTLE_ENDIAN 0
# define HASH_BIG_ENDIAN 0
# endif
#endif
#define rot(x,k) (((x)<<(k)) ^ ((x)>>(32-(k))))
/*
-------------------------------------------------------------------------------
mix -- mix 3 32-bit values reversibly.
This is reversible, so any information in (a,b,c) before mix() is
still in (a,b,c) after mix().
If four pairs of (a,b,c) inputs are run through mix(), or through
mix() in reverse, there are at least 32 bits of the output that
are sometimes the same for one pair and different for another pair.
This was tested for:
* pairs that differed by one bit, by two bits, in any combination
of top bits of (a,b,c), or in any combination of bottom bits of
(a,b,c).
* "differ" is defined as +, -, ^, or ~^. For + and -, I transformed
the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
is commonly produced by subtraction) look like a single 1-bit
difference.
* the base values were pseudorandom, all zero but one bit set, or
all zero plus a counter that starts at zero.
Some k values for my "a-=c; a^=rot(c,k); c+=b;" arrangement that
satisfy this are
4 6 8 16 19 4
9 15 3 18 27 15
14 9 3 7 17 3
Well, "9 15 3 18 27 15" didn't quite get 32 bits diffing
for "differ" defined as + with a one-bit base and a two-bit delta. I
used http://burtleburtle.net/bob/hash/avalanche.html to choose
the operations, constants, and arrangements of the variables.
This does not achieve avalanche. There are input bits of (a,b,c)
that fail to affect some output bits of (a,b,c), especially of a. The
most thoroughly mixed value is c, but it doesn't really even achieve
avalanche in c.
This allows some parallelism. Read-after-writes are good at doubling
the number of bits affected, so the goal of mixing pulls in the opposite
direction as the goal of parallelism. I did what I could. Rotates
seem to cost as much as shifts on every machine I could lay my hands
on, and rotates are much kinder to the top and bottom bits, so I used
rotates.
-------------------------------------------------------------------------------
*/
#define mix(a,b,c)
{
a -= c; a ^= rot(c, 4); c += b;
b -= a; b ^= rot(a, 6); a += c;
c -= b; c ^= rot(b, 8); b += a;
a -= c; a ^= rot(c,16); c += b;
b -= a; b ^= rot(a,19); a += c;
c -= b; c ^= rot(b, 4); b += a;
}
/*
-------------------------------------------------------------------------------
final -- final mixing of 3 32-bit values (a,b,c) into c
Pairs of (a,b,c) values differing in only a few bits will usually
produce values of c that look totally different. This was tested for
* pairs that differed by one bit, by two bits, in any combination
of top bits of (a,b,c), or in any combination of bottom bits of
(a,b,c).
* "differ" is defined as +, -, ^, or ~^. For + and -, I transformed
the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
is commonly produced by subtraction) look like a single 1-bit
difference.
* the base values were pseudorandom, all zero but one bit set, or
all zero plus a counter that starts at zero.
These constants passed:
14 11 25 16 4 14 24
12 14 25 16 4 14 24
and these came close:
4 8 15 26 3 22 24
10 8 15 26 3 22 24
11 8 15 26 3 22 24
-------------------------------------------------------------------------------
*/
#define final(a,b,c)
{
c ^= b; c -= rot(b,14);
a ^= c; a -= rot(c,11);
b ^= a; b -= rot(a,25);
c ^= b; c -= rot(b,16);
a ^= c; a -= rot(c,4);
b ^= a; b -= rot(a,14);
c ^= b; c -= rot(b,24);
}
#if HASH_LITTLE_ENDIAN == 1
uint32_t jenkins_hash(
const void *key, /* the key to hash */
size_t length) /* length of the key */
{
uint32_t a,b,c; /* internal state */
union { const void *ptr; size_t i; } u; /* needed for Mac Powerbook G4 */
/* Set up the internal state */
a = b = c = 0xdeadbeef + ((uint32_t)length) + 0;
u.ptr = key;
if (HASH_LITTLE_ENDIAN && ((u.i & 0x3) == 0)) {
const uint32_t *k = key; /* read 32-bit chunks */
#ifdef VALGRIND
const uint8_t *k8;
#endif /* ifdef VALGRIND */
/*------ all but last block: aligned reads and affect 32 bits of (a,b,c) */
while (length > 12)
{
a += k[0];
b += k[1];
c += k[2];
mix(a,b,c);
length -= 12;
k += 3;
}
/*----------------------------- handle the last (probably partial) block */
/*
* "k[2]&0xffffff" actually reads beyond the end of the string, but
* then masks off the part it's not allowed to read. Because the
* string is aligned, the masked-off tail is in the same word as the
* rest of the string. Every machine with memory protection I've seen
* does it on word boundaries, so is OK with this. But VALGRIND will
* still catch it and complain. The masking trick does make the hash
* noticeably faster for short strings (like English words).
*/
#ifndef VALGRIND
switch(length)
{
case 12: c+=k[2]; b+=k[1]; a+=k[0]; break;
case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break;
case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break;
case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break;
case 8 : b+=k[1]; a+=k[0]; break;
case 7 : b+=k[1]&0xffffff; a+=k[0]; break;
case 6 : b+=k[1]&0xffff; a+=k[0]; break;
case 5 : b+=k[1]&0xff; a+=k[0]; break;
case 4 : a+=k[0]; break;
case 3 : a+=k[0]&0xffffff; break;
case 2 : a+=k[0]&0xffff; break;
case 1 : a+=k[0]&0xff; break;
case 0 : return c; /* zero length strings require no mixing */
}
#else /* make valgrind happy */
k8 = (const uint8_t *)k;
switch(length)
{
case 12: c+=k[2]; b+=k[1]; a+=k[0];