postgresql/src/include/access/brin_page.h

71 lines
1.8 KiB
C
Raw Normal View History

BRIN: Block Range Indexes BRIN is a new index access method intended to accelerate scans of very large tables, without the maintenance overhead of btrees or other traditional indexes. They work by maintaining "summary" data about block ranges. Bitmap index scans work by reading each summary tuple and comparing them with the query quals; all pages in the range are returned in a lossy TID bitmap if the quals are consistent with the values in the summary tuple, otherwise not. Normal index scans are not supported because these indexes do not store TIDs. As new tuples are added into the index, the summary information is updated (if the block range in which the tuple is added is already summarized) or not; in the latter case, a subsequent pass of VACUUM or the brin_summarize_new_values() function will create the summary information. For data types with natural 1-D sort orders, the summary info consists of the maximum and the minimum values of each indexed column within each page range. This type of operator class we call "Minmax", and we supply a bunch of them for most data types with B-tree opclasses. Since the BRIN code is generalized, other approaches are possible for things such as arrays, geometric types, ranges, etc; even for things such as enum types we could do something different than minmax with better results. In this commit I only include minmax. Catalog version bumped due to new builtin catalog entries. There's more that could be done here, but this is a good step forwards. Loosely based on ideas from Simon Riggs; code mostly by Álvaro Herrera, with contribution by Heikki Linnakangas. Patch reviewed by: Amit Kapila, Heikki Linnakangas, Robert Haas. Testing help from Jeff Janes, Erik Rijkers, Emanuel Calvo. PS: The research leading to these results has received funding from the European Union's Seventh Framework Programme (FP7/2007-2013) under grant agreement n° 318633.
2014-11-07 20:38:14 +01:00
/*
* brin_page.h
* Prototypes and definitions for BRIN page layouts
*
* Portions Copyright (c) 1996-2015, PostgreSQL Global Development Group
BRIN: Block Range Indexes BRIN is a new index access method intended to accelerate scans of very large tables, without the maintenance overhead of btrees or other traditional indexes. They work by maintaining "summary" data about block ranges. Bitmap index scans work by reading each summary tuple and comparing them with the query quals; all pages in the range are returned in a lossy TID bitmap if the quals are consistent with the values in the summary tuple, otherwise not. Normal index scans are not supported because these indexes do not store TIDs. As new tuples are added into the index, the summary information is updated (if the block range in which the tuple is added is already summarized) or not; in the latter case, a subsequent pass of VACUUM or the brin_summarize_new_values() function will create the summary information. For data types with natural 1-D sort orders, the summary info consists of the maximum and the minimum values of each indexed column within each page range. This type of operator class we call "Minmax", and we supply a bunch of them for most data types with B-tree opclasses. Since the BRIN code is generalized, other approaches are possible for things such as arrays, geometric types, ranges, etc; even for things such as enum types we could do something different than minmax with better results. In this commit I only include minmax. Catalog version bumped due to new builtin catalog entries. There's more that could be done here, but this is a good step forwards. Loosely based on ideas from Simon Riggs; code mostly by Álvaro Herrera, with contribution by Heikki Linnakangas. Patch reviewed by: Amit Kapila, Heikki Linnakangas, Robert Haas. Testing help from Jeff Janes, Erik Rijkers, Emanuel Calvo. PS: The research leading to these results has received funding from the European Union's Seventh Framework Programme (FP7/2007-2013) under grant agreement n° 318633.
2014-11-07 20:38:14 +01:00
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* src/include/access/brin_page.h
*
* NOTES
*
* These structs should really be private to specific BRIN files, but it's
* useful to have them here so that they can be used by pageinspect and similar
* tools.
*/
#ifndef BRIN_PAGE_H
#define BRIN_PAGE_H
#include "storage/block.h"
#include "storage/itemptr.h"
/* special space on all BRIN pages stores a "type" identifier */
#define BRIN_PAGETYPE_META 0xF091
#define BRIN_PAGETYPE_REVMAP 0xF092
#define BRIN_PAGETYPE_REGULAR 0xF093
#define BRIN_PAGE_TYPE(page) \
(((BrinSpecialSpace *) PageGetSpecialPointer(page))->type)
#define BRIN_IS_REVMAP_PAGE(page) (BRIN_PAGE_TYPE(page) == BRIN_PAGETYPE_REVMAP)
#define BRIN_IS_REGULAR_PAGE(page) (BRIN_PAGE_TYPE(page) == BRIN_PAGETYPE_REGULAR)
/* flags for BrinSpecialSpace */
#define BRIN_EVACUATE_PAGE (1 << 0)
typedef struct BrinSpecialSpace
{
uint16 flags;
uint16 type;
} BrinSpecialSpace;
/* Metapage definitions */
typedef struct BrinMetaPageData
{
uint32 brinMagic;
uint32 brinVersion;
BlockNumber pagesPerRange;
BlockNumber lastRevmapPage;
} BrinMetaPageData;
#define BRIN_CURRENT_VERSION 1
#define BRIN_META_MAGIC 0xA8109CFA
#define BRIN_METAPAGE_BLKNO 0
/* Definitions for revmap pages */
typedef struct RevmapContents
{
ItemPointerData rm_tids[1]; /* really REVMAP_PAGE_MAXITEMS */
} RevmapContents;
#define REVMAP_CONTENT_SIZE \
(BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - \
offsetof(RevmapContents, rm_tids) - \
MAXALIGN(sizeof(BrinSpecialSpace)))
/* max num of items in the array */
#define REVMAP_PAGE_MAXITEMS \
(REVMAP_CONTENT_SIZE / sizeof(ItemPointerData))
#endif /* BRIN_PAGE_H */