1
0
mirror of https://github.com/postgres/postgres.git synced 2025-08-21 10:42:50 +03:00

Improve handling of NULLs in KNN-GiST and KNN-SP-GiST

This commit improves subject in two ways:

 * It removes ugliness of 02f90879e7, which stores distance values and null
   flags in two separate arrays after GISTSearchItem struct.  Instead we pack
   both distance value and null flag in IndexOrderByDistance struct.  Alignment
   overhead should be negligible, because we typically deal with at most few
   "col op const" expressions in ORDER BY clause.
 * It fixes handling of "col op NULL" expression in KNN-SP-GiST.  Now, these
   expression are not passed to support functions, which can't deal with them.
   Instead, NULL result is implicitly assumed.  It future we may decide to
   teach support functions to deal with NULL arguments, but current solution is
   bugfix suitable for backpatch.

Reported-by: Nikita Glukhov
Discussion: https://postgr.es/m/826f57ee-afc7-8977-c44c-6111d18b02ec%40postgrespro.ru
Author: Nikita Glukhov
Reviewed-by: Alexander Korotkov
Backpatch-through: 9.4
This commit is contained in:
Alexander Korotkov
2019-09-19 21:30:19 +03:00
parent b9cf94c8c2
commit 31cbd76057
10 changed files with 140 additions and 101 deletions

View File

@@ -118,6 +118,13 @@ typedef enum IndexUniqueCheck
} IndexUniqueCheck;
/* Nullable "ORDER BY col op const" distance */
typedef struct IndexOrderByDistance
{
double value;
bool isnull;
} IndexOrderByDistance;
/*
* generalized index_ interface routines (in indexam.c)
*/
@@ -179,8 +186,7 @@ extern FmgrInfo *index_getprocinfo(Relation irel, AttrNumber attnum,
uint16 procnum);
extern void index_store_float8_orderby_distances(IndexScanDesc scan,
Oid *orderByTypes,
double *distanceValues,
bool *distanceNulls,
IndexOrderByDistance *distances,
bool recheckOrderBy);
/*

View File

@@ -139,29 +139,15 @@ typedef struct GISTSearchItem
GISTSearchHeapItem heap; /* heap info, if heap tuple */
} data;
/*
* This data structure is followed by arrays of distance values and
* distance null flags. Size of both arrays is
* IndexScanDesc->numberOfOrderBys. See macros below for accessing those
* arrays.
*/
/* numberOfOrderBys entries */
IndexOrderByDistance distances[FLEXIBLE_ARRAY_MEMBER];
} GISTSearchItem;
#define GISTSearchItemIsHeap(item) ((item).blkno == InvalidBlockNumber)
#define SizeOfGISTSearchItem(n_distances) (DOUBLEALIGN(sizeof(GISTSearchItem)) + \
(sizeof(double) + sizeof(bool)) * (n_distances))
/*
* We actually don't need n_distances compute pointer to distance values.
* Nevertheless take n_distances as argument to have same arguments list for
* GISTSearchItemDistanceValues() and GISTSearchItemDistanceNulls().
*/
#define GISTSearchItemDistanceValues(item, n_distances) \
((double *) ((Pointer) (item) + DOUBLEALIGN(sizeof(GISTSearchItem))))
#define GISTSearchItemDistanceNulls(item, n_distances) \
((bool *) ((Pointer) (item) + DOUBLEALIGN(sizeof(GISTSearchItem)) + sizeof(double) * (n_distances)))
#define SizeOfGISTSearchItem(n_distances) \
(offsetof(GISTSearchItem, distances) + \
sizeof(IndexOrderByDistance) * (n_distances))
/*
* GISTScanOpaqueData: private state for a scan of a GiST index
@@ -177,8 +163,7 @@ typedef struct GISTScanOpaqueData
bool firstCall; /* true until first gistgettuple call */
/* pre-allocated workspace arrays */
double *distanceValues; /* output area for gistindex_keytest */
bool *distanceNulls;
IndexOrderByDistance *distances; /* output area for gistindex_keytest */
/* info about killed items if any (killedItems is NULL if never used) */
OffsetNumber *killedItems; /* offset numbers of killed items */

View File

@@ -169,8 +169,12 @@ typedef struct SpGistScanOpaqueData
int numberOfKeys; /* number of index qualifier conditions */
ScanKey keyData; /* array of index qualifier descriptors */
int numberOfOrderBys; /* number of ordering operators */
int numberOfNonNullOrderBys; /* number of ordering operators
* with non-NULL arguments */
ScanKey orderByData; /* array of ordering op descriptors */
Oid *orderByTypes; /* array of ordering op return types */
int *nonNullOrderByOffsets; /* array of offset of non-NULL
* ordering keys in the original array */
Oid indexCollation; /* collation of index column */
/* Opclass defined functions: */
@@ -195,7 +199,9 @@ typedef struct SpGistScanOpaqueData
bool recheckDistances[MaxIndexTuplesPerPage]; /* distance recheck
* flags */
HeapTuple reconTups[MaxIndexTuplesPerPage]; /* reconstructed tuples */
double *distances[MaxIndexTuplesPerPage]; /* distances (for recheck) */
/* distances (for recheck) */
IndexOrderByDistance *distances[MaxIndexTuplesPerPage];
/*
* Note: using MaxIndexTuplesPerPage above is a bit hokey since