mirror of https://github.com/postgres/postgres
Move hash_any prototype from access/hash.h to utils/hashutils.h
... as well as its implementation from backend/access/hash/hashfunc.c to backend/utils/hash/hashfn.c. access/hash is the place for the hash index AM, not really appropriate for generic facilities, which is what hash_any is; having things the old way meant that anything using hash_any had to include the AM's include file, pointlessly polluting its namespace with unrelated, unnecessary cruft. Also move the HTEqual strategy number to access/stratnum.h from access/hash.h. To avoid breaking third-party extension code, add an #include "utils/hashutils.h" to access/hash.h. (An easily removed line by committers who enjoy their asbestos suits to protect them from angry extension authors.) Discussion: https://postgr.es/m/201901251935.ser5e4h6djt2@alvherre.pgsql
This commit is contained in:
parent
b212245f96
commit
af38498d4c
|
@ -3,10 +3,10 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "catalog/pg_collation.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/formatting.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/varlena.h"
|
||||
|
||||
PG_MODULE_MAGIC;
|
||||
|
|
|
@ -3,11 +3,11 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/htup_details.h"
|
||||
#include "catalog/pg_type.h"
|
||||
#include "funcapi.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/memutils.h"
|
||||
|
||||
#include "hstore.h"
|
||||
|
|
|
@ -61,7 +61,6 @@
|
|||
#include <sys/stat.h>
|
||||
#include <unistd.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "catalog/pg_authid.h"
|
||||
#include "executor/instrument.h"
|
||||
#include "funcapi.h"
|
||||
|
@ -78,6 +77,7 @@
|
|||
#include "tcop/utility.h"
|
||||
#include "utils/acl.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/memutils.h"
|
||||
|
||||
PG_MODULE_MAGIC;
|
||||
|
|
|
@ -12,11 +12,11 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "catalog/pg_proc.h"
|
||||
#include "commands/seclabel.h"
|
||||
#include "storage/ipc.h"
|
||||
#include "utils/guc.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/memutils.h"
|
||||
|
||||
#include "sepgsql.h"
|
||||
|
|
|
@ -19,7 +19,6 @@
|
|||
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/htup_details.h"
|
||||
#include "access/tupdesc_details.h"
|
||||
#include "catalog/pg_collation.h"
|
||||
|
|
|
@ -28,6 +28,7 @@
|
|||
|
||||
#include "access/hash.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/hashutils.h"
|
||||
|
||||
/*
|
||||
* Datatype-specific hash functions.
|
||||
|
@ -307,629 +308,3 @@ hashvarlenaextended(PG_FUNCTION_ARGS)
|
|||
|
||||
return result;
|
||||
}
|
||||
|
||||
/*
|
||||
* This hash function was written by Bob Jenkins
|
||||
* (bob_jenkins@burtleburtle.net), and superficially adapted
|
||||
* for PostgreSQL by Neil Conway. For more information on this
|
||||
* hash function, see http://burtleburtle.net/bob/hash/doobs.html,
|
||||
* or Bob's article in Dr. Dobb's Journal, Sept. 1997.
|
||||
*
|
||||
* In the current code, we have adopted Bob's 2006 update of his hash
|
||||
* function to fetch the data a word at a time when it is suitably aligned.
|
||||
* This makes for a useful speedup, at the cost of having to maintain
|
||||
* four code paths (aligned vs unaligned, and little-endian vs big-endian).
|
||||
* It also uses two separate mixing functions mix() and final(), instead
|
||||
* of a slower multi-purpose function.
|
||||
*/
|
||||
|
||||
/* Get a bit mask of the bits set in non-uint32 aligned addresses */
|
||||
#define UINT32_ALIGN_MASK (sizeof(uint32) - 1)
|
||||
|
||||
/* Rotate a uint32 value left by k bits - note multiple evaluation! */
|
||||
#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.
|
||||
*
|
||||
* 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 from 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.
|
||||
*
|
||||
* The use of separate functions for mix() and final() allow for a
|
||||
* substantial performance increase since final() does not need to
|
||||
* do well in reverse, but is does need to affect all output bits.
|
||||
* mix(), on the other hand, does not need to affect all output
|
||||
* bits (affecting 32 bits is enough). The original hash function had
|
||||
* a single mixing operation that had to satisfy both sets of requirements
|
||||
* and was slower as a result.
|
||||
*----------
|
||||
*/
|
||||
#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); \
|
||||
}
|
||||
|
||||
/*
|
||||
* hash_any() -- hash a variable-length key into a 32-bit value
|
||||
* k : the key (the unaligned variable-length array of bytes)
|
||||
* len : the length of the key, counting by bytes
|
||||
*
|
||||
* Returns a uint32 value. Every bit of the key affects every bit of
|
||||
* the return value. Every 1-bit and 2-bit delta achieves avalanche.
|
||||
* About 6*len+35 instructions. The best hash table sizes are powers
|
||||
* of 2. There is no need to do mod a prime (mod is sooo slow!).
|
||||
* If you need less than 32 bits, use a bitmask.
|
||||
*
|
||||
* This procedure must never throw elog(ERROR); the ResourceOwner code
|
||||
* relies on this not to fail.
|
||||
*
|
||||
* Note: we could easily change this function to return a 64-bit hash value
|
||||
* by using the final values of both b and c. b is perhaps a little less
|
||||
* well mixed than c, however.
|
||||
*/
|
||||
Datum
|
||||
hash_any(register const unsigned char *k, register int keylen)
|
||||
{
|
||||
register uint32 a,
|
||||
b,
|
||||
c,
|
||||
len;
|
||||
|
||||
/* Set up the internal state */
|
||||
len = keylen;
|
||||
a = b = c = 0x9e3779b9 + len + 3923095;
|
||||
|
||||
/* If the source pointer is word-aligned, we use word-wide fetches */
|
||||
if (((uintptr_t) k & UINT32_ALIGN_MASK) == 0)
|
||||
{
|
||||
/* Code path for aligned source data */
|
||||
register const uint32 *ka = (const uint32 *) k;
|
||||
|
||||
/* handle most of the key */
|
||||
while (len >= 12)
|
||||
{
|
||||
a += ka[0];
|
||||
b += ka[1];
|
||||
c += ka[2];
|
||||
mix(a, b, c);
|
||||
ka += 3;
|
||||
len -= 12;
|
||||
}
|
||||
|
||||
/* handle the last 11 bytes */
|
||||
k = (const unsigned char *) ka;
|
||||
#ifdef WORDS_BIGENDIAN
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 8);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 24);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += ka[1];
|
||||
a += ka[0];
|
||||
break;
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 8);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 16);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += ((uint32) k[4] << 24);
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += ka[0];
|
||||
break;
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 8);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 16);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += ((uint32) k[0] << 24);
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#else /* !WORDS_BIGENDIAN */
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 24);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 8);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += ka[1];
|
||||
a += ka[0];
|
||||
break;
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 16);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 8);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += k[4];
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += ka[0];
|
||||
break;
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 16);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 8);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += k[0];
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#endif /* WORDS_BIGENDIAN */
|
||||
}
|
||||
else
|
||||
{
|
||||
/* Code path for non-aligned source data */
|
||||
|
||||
/* handle most of the key */
|
||||
while (len >= 12)
|
||||
{
|
||||
#ifdef WORDS_BIGENDIAN
|
||||
a += (k[3] + ((uint32) k[2] << 8) + ((uint32) k[1] << 16) + ((uint32) k[0] << 24));
|
||||
b += (k[7] + ((uint32) k[6] << 8) + ((uint32) k[5] << 16) + ((uint32) k[4] << 24));
|
||||
c += (k[11] + ((uint32) k[10] << 8) + ((uint32) k[9] << 16) + ((uint32) k[8] << 24));
|
||||
#else /* !WORDS_BIGENDIAN */
|
||||
a += (k[0] + ((uint32) k[1] << 8) + ((uint32) k[2] << 16) + ((uint32) k[3] << 24));
|
||||
b += (k[4] + ((uint32) k[5] << 8) + ((uint32) k[6] << 16) + ((uint32) k[7] << 24));
|
||||
c += (k[8] + ((uint32) k[9] << 8) + ((uint32) k[10] << 16) + ((uint32) k[11] << 24));
|
||||
#endif /* WORDS_BIGENDIAN */
|
||||
mix(a, b, c);
|
||||
k += 12;
|
||||
len -= 12;
|
||||
}
|
||||
|
||||
/* handle the last 11 bytes */
|
||||
#ifdef WORDS_BIGENDIAN
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 8);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 24);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += k[7];
|
||||
/* fall through */
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 8);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 16);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += ((uint32) k[4] << 24);
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += k[3];
|
||||
/* fall through */
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 8);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 16);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += ((uint32) k[0] << 24);
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#else /* !WORDS_BIGENDIAN */
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 24);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 8);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += ((uint32) k[7] << 24);
|
||||
/* fall through */
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 16);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 8);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += k[4];
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += ((uint32) k[3] << 24);
|
||||
/* fall through */
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 16);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 8);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += k[0];
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#endif /* WORDS_BIGENDIAN */
|
||||
}
|
||||
|
||||
final(a, b, c);
|
||||
|
||||
/* report the result */
|
||||
return UInt32GetDatum(c);
|
||||
}
|
||||
|
||||
/*
|
||||
* hash_any_extended() -- hash into a 64-bit value, using an optional seed
|
||||
* k : the key (the unaligned variable-length array of bytes)
|
||||
* len : the length of the key, counting by bytes
|
||||
* seed : a 64-bit seed (0 means no seed)
|
||||
*
|
||||
* Returns a uint64 value. Otherwise similar to hash_any.
|
||||
*/
|
||||
Datum
|
||||
hash_any_extended(register const unsigned char *k, register int keylen,
|
||||
uint64 seed)
|
||||
{
|
||||
register uint32 a,
|
||||
b,
|
||||
c,
|
||||
len;
|
||||
|
||||
/* Set up the internal state */
|
||||
len = keylen;
|
||||
a = b = c = 0x9e3779b9 + len + 3923095;
|
||||
|
||||
/* If the seed is non-zero, use it to perturb the internal state. */
|
||||
if (seed != 0)
|
||||
{
|
||||
/*
|
||||
* In essence, the seed is treated as part of the data being hashed,
|
||||
* but for simplicity, we pretend that it's padded with four bytes of
|
||||
* zeroes so that the seed constitutes a 12-byte chunk.
|
||||
*/
|
||||
a += (uint32) (seed >> 32);
|
||||
b += (uint32) seed;
|
||||
mix(a, b, c);
|
||||
}
|
||||
|
||||
/* If the source pointer is word-aligned, we use word-wide fetches */
|
||||
if (((uintptr_t) k & UINT32_ALIGN_MASK) == 0)
|
||||
{
|
||||
/* Code path for aligned source data */
|
||||
register const uint32 *ka = (const uint32 *) k;
|
||||
|
||||
/* handle most of the key */
|
||||
while (len >= 12)
|
||||
{
|
||||
a += ka[0];
|
||||
b += ka[1];
|
||||
c += ka[2];
|
||||
mix(a, b, c);
|
||||
ka += 3;
|
||||
len -= 12;
|
||||
}
|
||||
|
||||
/* handle the last 11 bytes */
|
||||
k = (const unsigned char *) ka;
|
||||
#ifdef WORDS_BIGENDIAN
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 8);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 24);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += ka[1];
|
||||
a += ka[0];
|
||||
break;
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 8);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 16);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += ((uint32) k[4] << 24);
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += ka[0];
|
||||
break;
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 8);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 16);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += ((uint32) k[0] << 24);
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#else /* !WORDS_BIGENDIAN */
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 24);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 8);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += ka[1];
|
||||
a += ka[0];
|
||||
break;
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 16);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 8);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += k[4];
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += ka[0];
|
||||
break;
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 16);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 8);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += k[0];
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#endif /* WORDS_BIGENDIAN */
|
||||
}
|
||||
else
|
||||
{
|
||||
/* Code path for non-aligned source data */
|
||||
|
||||
/* handle most of the key */
|
||||
while (len >= 12)
|
||||
{
|
||||
#ifdef WORDS_BIGENDIAN
|
||||
a += (k[3] + ((uint32) k[2] << 8) + ((uint32) k[1] << 16) + ((uint32) k[0] << 24));
|
||||
b += (k[7] + ((uint32) k[6] << 8) + ((uint32) k[5] << 16) + ((uint32) k[4] << 24));
|
||||
c += (k[11] + ((uint32) k[10] << 8) + ((uint32) k[9] << 16) + ((uint32) k[8] << 24));
|
||||
#else /* !WORDS_BIGENDIAN */
|
||||
a += (k[0] + ((uint32) k[1] << 8) + ((uint32) k[2] << 16) + ((uint32) k[3] << 24));
|
||||
b += (k[4] + ((uint32) k[5] << 8) + ((uint32) k[6] << 16) + ((uint32) k[7] << 24));
|
||||
c += (k[8] + ((uint32) k[9] << 8) + ((uint32) k[10] << 16) + ((uint32) k[11] << 24));
|
||||
#endif /* WORDS_BIGENDIAN */
|
||||
mix(a, b, c);
|
||||
k += 12;
|
||||
len -= 12;
|
||||
}
|
||||
|
||||
/* handle the last 11 bytes */
|
||||
#ifdef WORDS_BIGENDIAN
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 8);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 24);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += k[7];
|
||||
/* fall through */
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 8);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 16);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += ((uint32) k[4] << 24);
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += k[3];
|
||||
/* fall through */
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 8);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 16);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += ((uint32) k[0] << 24);
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#else /* !WORDS_BIGENDIAN */
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 24);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 8);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += ((uint32) k[7] << 24);
|
||||
/* fall through */
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 16);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 8);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += k[4];
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += ((uint32) k[3] << 24);
|
||||
/* fall through */
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 16);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 8);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += k[0];
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#endif /* WORDS_BIGENDIAN */
|
||||
}
|
||||
|
||||
final(a, b, c);
|
||||
|
||||
/* report the result */
|
||||
PG_RETURN_UINT64(((uint64) b << 32) | c);
|
||||
}
|
||||
|
||||
/*
|
||||
* hash_uint32() -- hash a 32-bit value to a 32-bit value
|
||||
*
|
||||
* This has the same result as
|
||||
* hash_any(&k, sizeof(uint32))
|
||||
* but is faster and doesn't force the caller to store k into memory.
|
||||
*/
|
||||
Datum
|
||||
hash_uint32(uint32 k)
|
||||
{
|
||||
register uint32 a,
|
||||
b,
|
||||
c;
|
||||
|
||||
a = b = c = 0x9e3779b9 + (uint32) sizeof(uint32) + 3923095;
|
||||
a += k;
|
||||
|
||||
final(a, b, c);
|
||||
|
||||
/* report the result */
|
||||
return UInt32GetDatum(c);
|
||||
}
|
||||
|
||||
/*
|
||||
* hash_uint32_extended() -- hash a 32-bit value to a 64-bit value, with a seed
|
||||
*
|
||||
* Like hash_uint32, this is a convenience function.
|
||||
*/
|
||||
Datum
|
||||
hash_uint32_extended(uint32 k, uint64 seed)
|
||||
{
|
||||
register uint32 a,
|
||||
b,
|
||||
c;
|
||||
|
||||
a = b = c = 0x9e3779b9 + (uint32) sizeof(uint32) + 3923095;
|
||||
|
||||
if (seed != 0)
|
||||
{
|
||||
a += (uint32) (seed >> 32);
|
||||
b += (uint32) seed;
|
||||
mix(a, b, c);
|
||||
}
|
||||
|
||||
a += k;
|
||||
|
||||
final(a, b, c);
|
||||
|
||||
/* report the result */
|
||||
PG_RETURN_UINT64(((uint64) b << 32) | c);
|
||||
}
|
||||
|
|
|
@ -26,11 +26,11 @@
|
|||
|
||||
#include <math.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/tsmapi.h"
|
||||
#include "catalog/pg_type.h"
|
||||
#include "optimizer/optimizer.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/hashutils.h"
|
||||
|
||||
|
||||
/* Private state */
|
||||
|
|
|
@ -26,13 +26,13 @@
|
|||
|
||||
#include <math.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/heapam.h"
|
||||
#include "access/relscan.h"
|
||||
#include "access/tsmapi.h"
|
||||
#include "catalog/pg_type.h"
|
||||
#include "optimizer/optimizer.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/hashutils.h"
|
||||
|
||||
|
||||
/* Private state */
|
||||
|
|
|
@ -18,7 +18,6 @@
|
|||
#include "miscadmin.h"
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/hash.h"
|
||||
#include "access/heapam.h"
|
||||
#include "access/htup_details.h"
|
||||
#include "access/xact.h"
|
||||
|
|
|
@ -18,7 +18,6 @@
|
|||
#include "miscadmin.h"
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/hash.h"
|
||||
#include "access/htup_details.h"
|
||||
#include "access/table.h"
|
||||
#include "access/xact.h"
|
||||
|
|
|
@ -18,7 +18,6 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/parallel.h"
|
||||
#include "executor/executor.h"
|
||||
#include "miscadmin.h"
|
||||
|
|
|
@ -14,7 +14,6 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/heapam.h"
|
||||
#include "access/relscan.h"
|
||||
#include "access/tsmapi.h"
|
||||
|
@ -22,6 +21,7 @@
|
|||
#include "executor/nodeSamplescan.h"
|
||||
#include "miscadmin.h"
|
||||
#include "pgstat.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "storage/predicate.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/rel.h"
|
||||
|
|
|
@ -35,9 +35,9 @@
|
|||
|
||||
#include <math.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "lib/bloomfilter.h"
|
||||
#include "port/pg_bitutils.h"
|
||||
#include "utils/hashutils.h"
|
||||
|
||||
#define MAX_HASH_FUNCS 10
|
||||
|
||||
|
|
|
@ -20,9 +20,10 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "nodes/bitmapset.h"
|
||||
#include "nodes/pg_list.h"
|
||||
#include "port/pg_bitutils.h"
|
||||
#include "utils/hashutils.h"
|
||||
|
||||
|
||||
#define WORDNUM(x) ((x) / BITS_PER_BITMAPWORD)
|
||||
|
|
|
@ -18,13 +18,15 @@
|
|||
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include <limits.h>
|
||||
|
||||
#include "catalog/pg_tablespace.h"
|
||||
#include "commands/tablespace.h"
|
||||
#include "miscadmin.h"
|
||||
#include "storage/dsm.h"
|
||||
#include "storage/sharedfileset.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/hashutils.h"
|
||||
|
||||
static void SharedFileSetOnDetach(dsm_segment *segment, Datum datum);
|
||||
static void SharedFileSetPath(char *path, SharedFileSet *fileset, Oid tablespace);
|
||||
|
|
|
@ -13,12 +13,12 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "catalog/pg_collation.h"
|
||||
#include "catalog/pg_operator.h"
|
||||
#include "commands/vacuum.h"
|
||||
#include "tsearch/ts_type.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/hashutils.h"
|
||||
|
||||
|
||||
/* A hash key for lexemes */
|
||||
|
|
|
@ -16,7 +16,6 @@
|
|||
|
||||
#include <ctype.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/htup_details.h"
|
||||
#include "catalog/catalog.h"
|
||||
#include "catalog/namespace.h"
|
||||
|
@ -33,6 +32,7 @@
|
|||
#include "utils/acl.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/catcache.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/inval.h"
|
||||
#include "utils/lsyscache.h"
|
||||
#include "utils/memutils.h"
|
||||
|
|
|
@ -17,7 +17,6 @@
|
|||
#include <ctype.h>
|
||||
#include <math.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/htup_details.h"
|
||||
#include "catalog/pg_type.h"
|
||||
#include "funcapi.h"
|
||||
|
|
|
@ -20,7 +20,6 @@
|
|||
#include <float.h>
|
||||
#include <time.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/xact.h"
|
||||
#include "libpq/pqformat.h"
|
||||
#include "miscadmin.h"
|
||||
|
@ -30,6 +29,7 @@
|
|||
#include "utils/builtins.h"
|
||||
#include "utils/date.h"
|
||||
#include "utils/datetime.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/sortsupport.h"
|
||||
|
||||
/*
|
||||
|
|
|
@ -14,11 +14,11 @@
|
|||
#include "postgres.h"
|
||||
|
||||
#include "access/gin.h"
|
||||
#include "access/hash.h"
|
||||
#include "access/stratnum.h"
|
||||
#include "catalog/pg_collation.h"
|
||||
#include "catalog/pg_type.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/jsonb.h"
|
||||
#include "utils/varlena.h"
|
||||
|
||||
|
|
|
@ -13,10 +13,10 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "catalog/pg_collation.h"
|
||||
#include "miscadmin.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/jsonb.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "utils/varlena.h"
|
||||
|
|
|
@ -13,12 +13,12 @@
|
|||
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "lib/hyperloglog.h"
|
||||
#include "libpq/pqformat.h"
|
||||
#include "port/pg_bswap.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/guc.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/inet.h"
|
||||
#include "utils/sortsupport.h"
|
||||
|
||||
|
|
|
@ -21,9 +21,9 @@
|
|||
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "libpq/pqformat.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/inet.h"
|
||||
|
||||
/*
|
||||
|
|
|
@ -12,7 +12,7 @@
|
|||
#include <netinet/in.h>
|
||||
#include <arpa/inet.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/stratnum.h"
|
||||
#include "catalog/pg_opfamily.h"
|
||||
#include "catalog/pg_type.h"
|
||||
#include "common/ip.h"
|
||||
|
@ -24,6 +24,7 @@
|
|||
#include "nodes/supportnodes.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/fmgroids.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/inet.h"
|
||||
#include "utils/lsyscache.h"
|
||||
|
||||
|
|
|
@ -26,7 +26,6 @@
|
|||
#include <limits.h>
|
||||
#include <math.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "catalog/pg_type.h"
|
||||
#include "common/int.h"
|
||||
#include "funcapi.h"
|
||||
|
@ -39,6 +38,7 @@
|
|||
#include "utils/builtins.h"
|
||||
#include "utils/float.h"
|
||||
#include "utils/guc.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/int8.h"
|
||||
#include "utils/numeric.h"
|
||||
#include "utils/sortsupport.h"
|
||||
|
|
|
@ -13,7 +13,6 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "funcapi.h"
|
||||
#include "libpq/pqformat.h"
|
||||
#include "utils/builtins.h"
|
||||
|
|
|
@ -30,12 +30,13 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/tupmacs.h"
|
||||
#include "lib/stringinfo.h"
|
||||
#include "libpq/pqformat.h"
|
||||
#include "miscadmin.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/date.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/int8.h"
|
||||
#include "utils/lsyscache.h"
|
||||
#include "utils/rangetypes.h"
|
||||
|
|
|
@ -20,7 +20,6 @@
|
|||
#include <math.h>
|
||||
#include <limits.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/heapam.h"
|
||||
#include "access/sysattr.h"
|
||||
#include "catalog/namespace.h"
|
||||
|
@ -30,6 +29,7 @@
|
|||
#include "parser/parsetree.h"
|
||||
#include "utils/acl.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/rel.h"
|
||||
#include "utils/snapmgr.h"
|
||||
#include "utils/varlena.h"
|
||||
|
|
|
@ -20,7 +20,6 @@
|
|||
#include <limits.h>
|
||||
#include <sys/time.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/xact.h"
|
||||
#include "catalog/pg_type.h"
|
||||
#include "common/int128.h"
|
||||
|
|
|
@ -13,12 +13,12 @@
|
|||
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "lib/hyperloglog.h"
|
||||
#include "libpq/pqformat.h"
|
||||
#include "port/pg_bswap.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/guc.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/sortsupport.h"
|
||||
#include "utils/uuid.h"
|
||||
|
||||
|
|
|
@ -14,8 +14,6 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/tuptoaster.h"
|
||||
#include "catalog/pg_collation.h"
|
||||
#include "catalog/pg_type.h"
|
||||
|
@ -24,6 +22,7 @@
|
|||
#include "nodes/supportnodes.h"
|
||||
#include "utils/array.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/varlena.h"
|
||||
#include "mb/pg_wchar.h"
|
||||
|
||||
|
|
|
@ -17,7 +17,6 @@
|
|||
#include <ctype.h>
|
||||
#include <limits.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/tuptoaster.h"
|
||||
#include "catalog/pg_collation.h"
|
||||
#include "catalog/pg_type.h"
|
||||
|
@ -30,6 +29,7 @@
|
|||
#include "regex/regex.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/bytea.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/lsyscache.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "utils/pg_locale.h"
|
||||
|
|
|
@ -15,7 +15,6 @@
|
|||
#include "postgres.h"
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/hash.h"
|
||||
#include "access/relscan.h"
|
||||
#include "access/sysattr.h"
|
||||
#include "access/table.h"
|
||||
|
|
|
@ -30,7 +30,6 @@
|
|||
#include <fcntl.h>
|
||||
#include <unistd.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/htup_details.h"
|
||||
#include "access/multixact.h"
|
||||
#include "access/nbtree.h"
|
||||
|
|
|
@ -1,7 +1,8 @@
|
|||
/*-------------------------------------------------------------------------
|
||||
*
|
||||
* hashfn.c
|
||||
* Hash functions for use in dynahash.c hashtables
|
||||
* Generic hashing functions, and hash functions for use in dynahash.c
|
||||
* hashtables
|
||||
*
|
||||
*
|
||||
* Portions Copyright (c) 1996-2019, PostgreSQL Global Development Group
|
||||
|
@ -21,10 +22,637 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "fmgr.h"
|
||||
#include "nodes/bitmapset.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/hsearch.h"
|
||||
|
||||
|
||||
/*
|
||||
* This hash function was written by Bob Jenkins
|
||||
* (bob_jenkins@burtleburtle.net), and superficially adapted
|
||||
* for PostgreSQL by Neil Conway. For more information on this
|
||||
* hash function, see http://burtleburtle.net/bob/hash/doobs.html,
|
||||
* or Bob's article in Dr. Dobb's Journal, Sept. 1997.
|
||||
*
|
||||
* In the current code, we have adopted Bob's 2006 update of his hash
|
||||
* function to fetch the data a word at a time when it is suitably aligned.
|
||||
* This makes for a useful speedup, at the cost of having to maintain
|
||||
* four code paths (aligned vs unaligned, and little-endian vs big-endian).
|
||||
* It also uses two separate mixing functions mix() and final(), instead
|
||||
* of a slower multi-purpose function.
|
||||
*/
|
||||
|
||||
/* Get a bit mask of the bits set in non-uint32 aligned addresses */
|
||||
#define UINT32_ALIGN_MASK (sizeof(uint32) - 1)
|
||||
|
||||
/* Rotate a uint32 value left by k bits - note multiple evaluation! */
|
||||
#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.
|
||||
*
|
||||
* 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 from 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.
|
||||
*
|
||||
* The use of separate functions for mix() and final() allow for a
|
||||
* substantial performance increase since final() does not need to
|
||||
* do well in reverse, but is does need to affect all output bits.
|
||||
* mix(), on the other hand, does not need to affect all output
|
||||
* bits (affecting 32 bits is enough). The original hash function had
|
||||
* a single mixing operation that had to satisfy both sets of requirements
|
||||
* and was slower as a result.
|
||||
*----------
|
||||
*/
|
||||
#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); \
|
||||
}
|
||||
|
||||
/*
|
||||
* hash_any() -- hash a variable-length key into a 32-bit value
|
||||
* k : the key (the unaligned variable-length array of bytes)
|
||||
* len : the length of the key, counting by bytes
|
||||
*
|
||||
* Returns a uint32 value. Every bit of the key affects every bit of
|
||||
* the return value. Every 1-bit and 2-bit delta achieves avalanche.
|
||||
* About 6*len+35 instructions. The best hash table sizes are powers
|
||||
* of 2. There is no need to do mod a prime (mod is sooo slow!).
|
||||
* If you need less than 32 bits, use a bitmask.
|
||||
*
|
||||
* This procedure must never throw elog(ERROR); the ResourceOwner code
|
||||
* relies on this not to fail.
|
||||
*
|
||||
* Note: we could easily change this function to return a 64-bit hash value
|
||||
* by using the final values of both b and c. b is perhaps a little less
|
||||
* well mixed than c, however.
|
||||
*/
|
||||
Datum
|
||||
hash_any(register const unsigned char *k, register int keylen)
|
||||
{
|
||||
register uint32 a,
|
||||
b,
|
||||
c,
|
||||
len;
|
||||
|
||||
/* Set up the internal state */
|
||||
len = keylen;
|
||||
a = b = c = 0x9e3779b9 + len + 3923095;
|
||||
|
||||
/* If the source pointer is word-aligned, we use word-wide fetches */
|
||||
if (((uintptr_t) k & UINT32_ALIGN_MASK) == 0)
|
||||
{
|
||||
/* Code path for aligned source data */
|
||||
register const uint32 *ka = (const uint32 *) k;
|
||||
|
||||
/* handle most of the key */
|
||||
while (len >= 12)
|
||||
{
|
||||
a += ka[0];
|
||||
b += ka[1];
|
||||
c += ka[2];
|
||||
mix(a, b, c);
|
||||
ka += 3;
|
||||
len -= 12;
|
||||
}
|
||||
|
||||
/* handle the last 11 bytes */
|
||||
k = (const unsigned char *) ka;
|
||||
#ifdef WORDS_BIGENDIAN
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 8);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 24);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += ka[1];
|
||||
a += ka[0];
|
||||
break;
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 8);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 16);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += ((uint32) k[4] << 24);
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += ka[0];
|
||||
break;
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 8);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 16);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += ((uint32) k[0] << 24);
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#else /* !WORDS_BIGENDIAN */
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 24);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 8);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += ka[1];
|
||||
a += ka[0];
|
||||
break;
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 16);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 8);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += k[4];
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += ka[0];
|
||||
break;
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 16);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 8);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += k[0];
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#endif /* WORDS_BIGENDIAN */
|
||||
}
|
||||
else
|
||||
{
|
||||
/* Code path for non-aligned source data */
|
||||
|
||||
/* handle most of the key */
|
||||
while (len >= 12)
|
||||
{
|
||||
#ifdef WORDS_BIGENDIAN
|
||||
a += (k[3] + ((uint32) k[2] << 8) + ((uint32) k[1] << 16) + ((uint32) k[0] << 24));
|
||||
b += (k[7] + ((uint32) k[6] << 8) + ((uint32) k[5] << 16) + ((uint32) k[4] << 24));
|
||||
c += (k[11] + ((uint32) k[10] << 8) + ((uint32) k[9] << 16) + ((uint32) k[8] << 24));
|
||||
#else /* !WORDS_BIGENDIAN */
|
||||
a += (k[0] + ((uint32) k[1] << 8) + ((uint32) k[2] << 16) + ((uint32) k[3] << 24));
|
||||
b += (k[4] + ((uint32) k[5] << 8) + ((uint32) k[6] << 16) + ((uint32) k[7] << 24));
|
||||
c += (k[8] + ((uint32) k[9] << 8) + ((uint32) k[10] << 16) + ((uint32) k[11] << 24));
|
||||
#endif /* WORDS_BIGENDIAN */
|
||||
mix(a, b, c);
|
||||
k += 12;
|
||||
len -= 12;
|
||||
}
|
||||
|
||||
/* handle the last 11 bytes */
|
||||
#ifdef WORDS_BIGENDIAN
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 8);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 24);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += k[7];
|
||||
/* fall through */
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 8);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 16);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += ((uint32) k[4] << 24);
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += k[3];
|
||||
/* fall through */
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 8);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 16);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += ((uint32) k[0] << 24);
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#else /* !WORDS_BIGENDIAN */
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 24);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 8);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += ((uint32) k[7] << 24);
|
||||
/* fall through */
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 16);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 8);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += k[4];
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += ((uint32) k[3] << 24);
|
||||
/* fall through */
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 16);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 8);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += k[0];
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#endif /* WORDS_BIGENDIAN */
|
||||
}
|
||||
|
||||
final(a, b, c);
|
||||
|
||||
/* report the result */
|
||||
return UInt32GetDatum(c);
|
||||
}
|
||||
|
||||
/*
|
||||
* hash_any_extended() -- hash into a 64-bit value, using an optional seed
|
||||
* k : the key (the unaligned variable-length array of bytes)
|
||||
* len : the length of the key, counting by bytes
|
||||
* seed : a 64-bit seed (0 means no seed)
|
||||
*
|
||||
* Returns a uint64 value. Otherwise similar to hash_any.
|
||||
*/
|
||||
Datum
|
||||
hash_any_extended(register const unsigned char *k, register int keylen,
|
||||
uint64 seed)
|
||||
{
|
||||
register uint32 a,
|
||||
b,
|
||||
c,
|
||||
len;
|
||||
|
||||
/* Set up the internal state */
|
||||
len = keylen;
|
||||
a = b = c = 0x9e3779b9 + len + 3923095;
|
||||
|
||||
/* If the seed is non-zero, use it to perturb the internal state. */
|
||||
if (seed != 0)
|
||||
{
|
||||
/*
|
||||
* In essence, the seed is treated as part of the data being hashed,
|
||||
* but for simplicity, we pretend that it's padded with four bytes of
|
||||
* zeroes so that the seed constitutes a 12-byte chunk.
|
||||
*/
|
||||
a += (uint32) (seed >> 32);
|
||||
b += (uint32) seed;
|
||||
mix(a, b, c);
|
||||
}
|
||||
|
||||
/* If the source pointer is word-aligned, we use word-wide fetches */
|
||||
if (((uintptr_t) k & UINT32_ALIGN_MASK) == 0)
|
||||
{
|
||||
/* Code path for aligned source data */
|
||||
register const uint32 *ka = (const uint32 *) k;
|
||||
|
||||
/* handle most of the key */
|
||||
while (len >= 12)
|
||||
{
|
||||
a += ka[0];
|
||||
b += ka[1];
|
||||
c += ka[2];
|
||||
mix(a, b, c);
|
||||
ka += 3;
|
||||
len -= 12;
|
||||
}
|
||||
|
||||
/* handle the last 11 bytes */
|
||||
k = (const unsigned char *) ka;
|
||||
#ifdef WORDS_BIGENDIAN
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 8);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 24);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += ka[1];
|
||||
a += ka[0];
|
||||
break;
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 8);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 16);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += ((uint32) k[4] << 24);
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += ka[0];
|
||||
break;
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 8);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 16);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += ((uint32) k[0] << 24);
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#else /* !WORDS_BIGENDIAN */
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 24);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 8);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += ka[1];
|
||||
a += ka[0];
|
||||
break;
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 16);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 8);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += k[4];
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += ka[0];
|
||||
break;
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 16);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 8);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += k[0];
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#endif /* WORDS_BIGENDIAN */
|
||||
}
|
||||
else
|
||||
{
|
||||
/* Code path for non-aligned source data */
|
||||
|
||||
/* handle most of the key */
|
||||
while (len >= 12)
|
||||
{
|
||||
#ifdef WORDS_BIGENDIAN
|
||||
a += (k[3] + ((uint32) k[2] << 8) + ((uint32) k[1] << 16) + ((uint32) k[0] << 24));
|
||||
b += (k[7] + ((uint32) k[6] << 8) + ((uint32) k[5] << 16) + ((uint32) k[4] << 24));
|
||||
c += (k[11] + ((uint32) k[10] << 8) + ((uint32) k[9] << 16) + ((uint32) k[8] << 24));
|
||||
#else /* !WORDS_BIGENDIAN */
|
||||
a += (k[0] + ((uint32) k[1] << 8) + ((uint32) k[2] << 16) + ((uint32) k[3] << 24));
|
||||
b += (k[4] + ((uint32) k[5] << 8) + ((uint32) k[6] << 16) + ((uint32) k[7] << 24));
|
||||
c += (k[8] + ((uint32) k[9] << 8) + ((uint32) k[10] << 16) + ((uint32) k[11] << 24));
|
||||
#endif /* WORDS_BIGENDIAN */
|
||||
mix(a, b, c);
|
||||
k += 12;
|
||||
len -= 12;
|
||||
}
|
||||
|
||||
/* handle the last 11 bytes */
|
||||
#ifdef WORDS_BIGENDIAN
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 8);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 24);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += k[7];
|
||||
/* fall through */
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 8);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 16);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += ((uint32) k[4] << 24);
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += k[3];
|
||||
/* fall through */
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 8);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 16);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += ((uint32) k[0] << 24);
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#else /* !WORDS_BIGENDIAN */
|
||||
switch (len)
|
||||
{
|
||||
case 11:
|
||||
c += ((uint32) k[10] << 24);
|
||||
/* fall through */
|
||||
case 10:
|
||||
c += ((uint32) k[9] << 16);
|
||||
/* fall through */
|
||||
case 9:
|
||||
c += ((uint32) k[8] << 8);
|
||||
/* fall through */
|
||||
case 8:
|
||||
/* the lowest byte of c is reserved for the length */
|
||||
b += ((uint32) k[7] << 24);
|
||||
/* fall through */
|
||||
case 7:
|
||||
b += ((uint32) k[6] << 16);
|
||||
/* fall through */
|
||||
case 6:
|
||||
b += ((uint32) k[5] << 8);
|
||||
/* fall through */
|
||||
case 5:
|
||||
b += k[4];
|
||||
/* fall through */
|
||||
case 4:
|
||||
a += ((uint32) k[3] << 24);
|
||||
/* fall through */
|
||||
case 3:
|
||||
a += ((uint32) k[2] << 16);
|
||||
/* fall through */
|
||||
case 2:
|
||||
a += ((uint32) k[1] << 8);
|
||||
/* fall through */
|
||||
case 1:
|
||||
a += k[0];
|
||||
/* case 0: nothing left to add */
|
||||
}
|
||||
#endif /* WORDS_BIGENDIAN */
|
||||
}
|
||||
|
||||
final(a, b, c);
|
||||
|
||||
/* report the result */
|
||||
PG_RETURN_UINT64(((uint64) b << 32) | c);
|
||||
}
|
||||
|
||||
/*
|
||||
* hash_uint32() -- hash a 32-bit value to a 32-bit value
|
||||
*
|
||||
* This has the same result as
|
||||
* hash_any(&k, sizeof(uint32))
|
||||
* but is faster and doesn't force the caller to store k into memory.
|
||||
*/
|
||||
Datum
|
||||
hash_uint32(uint32 k)
|
||||
{
|
||||
register uint32 a,
|
||||
b,
|
||||
c;
|
||||
|
||||
a = b = c = 0x9e3779b9 + (uint32) sizeof(uint32) + 3923095;
|
||||
a += k;
|
||||
|
||||
final(a, b, c);
|
||||
|
||||
/* report the result */
|
||||
return UInt32GetDatum(c);
|
||||
}
|
||||
|
||||
/*
|
||||
* hash_uint32_extended() -- hash a 32-bit value to a 64-bit value, with a seed
|
||||
*
|
||||
* Like hash_uint32, this is a convenience function.
|
||||
*/
|
||||
Datum
|
||||
hash_uint32_extended(uint32 k, uint64 seed)
|
||||
{
|
||||
register uint32 a,
|
||||
b,
|
||||
c;
|
||||
|
||||
a = b = c = 0x9e3779b9 + (uint32) sizeof(uint32) + 3923095;
|
||||
|
||||
if (seed != 0)
|
||||
{
|
||||
a += (uint32) (seed >> 32);
|
||||
b += (uint32) seed;
|
||||
mix(a, b, c);
|
||||
}
|
||||
|
||||
a += k;
|
||||
|
||||
final(a, b, c);
|
||||
|
||||
/* report the result */
|
||||
PG_RETURN_UINT64(((uint64) b << 32) | c);
|
||||
}
|
||||
/*
|
||||
* string_hash: hash function for keys that are NUL-terminated strings.
|
||||
*
|
||||
|
|
|
@ -20,11 +20,12 @@
|
|||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "jit/jit.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "storage/ipc.h"
|
||||
#include "storage/predicate.h"
|
||||
#include "storage/proc.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "utils/rel.h"
|
||||
#include "utils/resowner_private.h"
|
||||
|
|
|
@ -96,9 +96,9 @@
|
|||
|
||||
#include <limits.h>
|
||||
|
||||
#include "access/hash.h"
|
||||
#include "access/htup_details.h"
|
||||
#include "access/nbtree.h"
|
||||
#include "access/hash.h"
|
||||
#include "catalog/index.h"
|
||||
#include "catalog/pg_am.h"
|
||||
#include "commands/tablespace.h"
|
||||
|
|
|
@ -24,6 +24,7 @@
|
|||
#include "lib/stringinfo.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "storage/lockdefs.h"
|
||||
#include "utils/hashutils.h"
|
||||
#include "utils/hsearch.h"
|
||||
#include "utils/relcache.h"
|
||||
|
||||
|
@ -38,17 +39,6 @@ typedef uint32 Bucket;
|
|||
#define BUCKET_TO_BLKNO(metap,B) \
|
||||
((BlockNumber) ((B) + ((B) ? (metap)->hashm_spares[_hash_spareindex((B)+1)-1] : 0)) + 1)
|
||||
|
||||
/*
|
||||
* Rotate the high 32 bits and the low 32 bits separately. The standard
|
||||
* hash function sometimes rotates the low 32 bits by one bit when
|
||||
* combining elements. We want extended hash functions to be compatible with
|
||||
* that algorithm when the seed is 0, so we can't just do a normal rotation.
|
||||
* This works, though.
|
||||
*/
|
||||
#define ROTATE_HIGH_AND_LOW_32BITS(v) \
|
||||
((((v) << 1) & UINT64CONST(0xfffffffefffffffe)) | \
|
||||
(((v) >> 31) & UINT64CONST(0x100000001)))
|
||||
|
||||
/*
|
||||
* Special space for hash index pages.
|
||||
*
|
||||
|
@ -333,12 +323,6 @@ typedef HashMetaPageData *HashMetaPage;
|
|||
#define HASH_WRITE BUFFER_LOCK_EXCLUSIVE
|
||||
#define HASH_NOLOCK (-1)
|
||||
|
||||
/*
|
||||
* Strategy number. There's only one valid strategy for hashing: equality.
|
||||
*/
|
||||
#define HTEqualStrategyNumber 1
|
||||
#define HTMaxStrategyNumber 1
|
||||
|
||||
/*
|
||||
* When a new operator class is declared, we require that the user supply
|
||||
* us with an amproc function for hashing a key of the new type, returning
|
||||
|
@ -380,12 +364,6 @@ extern IndexBulkDeleteResult *hashvacuumcleanup(IndexVacuumInfo *info,
|
|||
extern bytea *hashoptions(Datum reloptions, bool validate);
|
||||
extern bool hashvalidate(Oid opclassoid);
|
||||
|
||||
extern Datum hash_any(register const unsigned char *k, register int keylen);
|
||||
extern Datum hash_any_extended(register const unsigned char *k,
|
||||
register int keylen, uint64 seed);
|
||||
extern Datum hash_uint32(uint32 k);
|
||||
extern Datum hash_uint32_extended(uint32 k, uint64 seed);
|
||||
|
||||
/* private routines */
|
||||
|
||||
/* hashinsert.c */
|
||||
|
|
|
@ -34,6 +34,13 @@ typedef uint16 StrategyNumber;
|
|||
|
||||
#define BTMaxStrategyNumber 5
|
||||
|
||||
/*
|
||||
* Strategy numbers for hash indexes. There's only one valid strategy for
|
||||
* hashing: equality.
|
||||
*/
|
||||
#define HTEqualStrategyNumber 1
|
||||
|
||||
#define HTMaxStrategyNumber 1
|
||||
|
||||
/*
|
||||
* Strategy numbers common to (some) GiST, SP-GiST and BRIN opclasses.
|
||||
|
|
|
@ -7,6 +7,25 @@
|
|||
#ifndef HASHUTILS_H
|
||||
#define HASHUTILS_H
|
||||
|
||||
|
||||
/*
|
||||
* Rotate the high 32 bits and the low 32 bits separately. The standard
|
||||
* hash function sometimes rotates the low 32 bits by one bit when
|
||||
* combining elements. We want extended hash functions to be compatible with
|
||||
* that algorithm when the seed is 0, so we can't just do a normal rotation.
|
||||
* This works, though.
|
||||
*/
|
||||
#define ROTATE_HIGH_AND_LOW_32BITS(v) \
|
||||
((((v) << 1) & UINT64CONST(0xfffffffefffffffe)) | \
|
||||
(((v) >> 31) & UINT64CONST(0x100000001)))
|
||||
|
||||
|
||||
extern Datum hash_any(register const unsigned char *k, register int keylen);
|
||||
extern Datum hash_any_extended(register const unsigned char *k,
|
||||
register int keylen, uint64 seed);
|
||||
extern Datum hash_uint32(uint32 k);
|
||||
extern Datum hash_uint32_extended(uint32 k, uint64 seed);
|
||||
|
||||
/*
|
||||
* Combine two 32-bit hash values, resulting in another hash value, with
|
||||
* decent bit mixing.
|
||||
|
|
Loading…
Reference in New Issue