database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-10-22 14:32:25 +03:00
Code Activity

Introduce 64-bit hash functions with a 64-bit seed.

Browse Source 
This will be useful for hash partitioning, which needs a way to seed
the hash functions to avoid problems such as a hash index on a hash
partitioned table clumping all values into a small portion of the
bucket space; it's also useful for anything that wants a 64-bit hash
value rather than a 32-bit hash value.

Just in case somebody wants a 64-bit hash value that is compatible
with the existing 32-bit hash values, make the low 32-bits of the
64-bit hash value match the 32-bit hash value when the seed is 0.

Robert Haas and Amul Sul

Discussion: http://postgr.es/m/CA+Tgmoafx2yoJuhCQQOL5CocEi-w_uG4S2xT0EtgiJnPGcHW3g@mail.gmail.com
This commit is contained in:
Robert Haas
2017-08-31 22:21:21 -04:00
parent 2d44c58c79
commit 81c5e46c49
33 changed files with 1555 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
src/include/access/hash.h
View File

@@ -38,6 +38,17 @@ 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.
*
@@ -289,12 +300,20 @@ typedef HashMetaPageData *HashMetaPage;
#define HTMaxStrategyNumber 1
/*
* When a new operator class is declared, we require that the user supply
* us with an amproc procudure for hashing a key of the new type.
* Since we only have one such proc in amproc, it's number 1.
* When a new operator class is declared, we require that the user supply
* us with an amproc procudure for hashing a key of the new type, returning
* a 32-bit hash value. We call this the "standard" hash procedure. We
* also allow an optional "extended" hash procedure which accepts a salt and
* returns a 64-bit hash value. This is highly recommended but, for reasons
* of backward compatibility, optional.
*
* When the salt is 0, the low 32 bits of the value returned by the extended
* hash procedure should match the value that would have been returned by the
* standard hash procedure.
*/
#define HASHPROC 1
#define HASHNProcs 1
#define HASHSTANDARD_PROC 1
#define HASHEXTENDED_PROC 2
#define HASHNProcs 2
/* public routines */
@@ -322,7 +341,10 @@ 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 */