From 078d759299ab76f1650309ffa4416f0c084be328 Mon Sep 17 00:00:00 2001 From: Heikki Linnakangas Date: Mon, 28 Sep 2020 11:01:45 +0300 Subject: [PATCH v2] Add functions to 'pageinspect' to inspect GiST indexes. --- contrib/pageinspect/Makefile | 6 +- contrib/pageinspect/expected/gist.out | 140 ++++++++++++++ contrib/pageinspect/gistfuncs.c | 173 ++++++++++++++++++ contrib/pageinspect/pageinspect--1.8--1.9.sql | 27 +++ contrib/pageinspect/pageinspect.control | 2 +- contrib/pageinspect/sql/gist.sql | 15 ++ doc/src/sgml/pageinspect.sgml | 60 ++++++ 7 files changed, 420 insertions(+), 3 deletions(-) create mode 100644 contrib/pageinspect/expected/gist.out create mode 100644 contrib/pageinspect/gistfuncs.c create mode 100644 contrib/pageinspect/pageinspect--1.8--1.9.sql create mode 100644 contrib/pageinspect/sql/gist.sql diff --git a/contrib/pageinspect/Makefile b/contrib/pageinspect/Makefile index d9d8177116..4539f0aef7 100644 --- a/contrib/pageinspect/Makefile +++ b/contrib/pageinspect/Makefile @@ -7,19 +7,21 @@ OBJS = \ btreefuncs.o \ fsmfuncs.o \ ginfuncs.o \ + gistfuncs.o \ hashfuncs.o \ heapfuncs.o \ rawpage.o EXTENSION = pageinspect -DATA = pageinspect--1.7--1.8.sql pageinspect--1.6--1.7.sql \ +DATA = pageinspect--1.8--1.9.sql \ + pageinspect--1.7--1.8.sql pageinspect--1.6--1.7.sql \ pageinspect--1.5.sql pageinspect--1.5--1.6.sql \ pageinspect--1.4--1.5.sql pageinspect--1.3--1.4.sql \ pageinspect--1.2--1.3.sql pageinspect--1.1--1.2.sql \ pageinspect--1.0--1.1.sql PGFILEDESC = "pageinspect - functions to inspect contents of database pages" -REGRESS = page btree brin gin hash checksum +REGRESS = page btree brin gin gist hash checksum ifdef USE_PGXS PG_CONFIG = pg_config diff --git a/contrib/pageinspect/expected/gist.out b/contrib/pageinspect/expected/gist.out new file mode 100644 index 0000000000..9bcb9d402e --- /dev/null +++ b/contrib/pageinspect/expected/gist.out @@ -0,0 +1,140 @@ +CREATE TABLE test_gist AS SELECT point(i,i) p, i::text t FROM + generate_series(1,1000) i; +CREATE INDEX test_gist_idx ON test_gist USING gist (p); +\x +SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 0)); +-[ RECORD 1 ]--------- +lsn | 0/1 +nsn | 0/0 +rightlink | 4294967295 +flags | {} + +SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 1)); +-[ RECORD 1 ]--------- +lsn | 0/1 +nsn | 0/0 +rightlink | 4294967295 +flags | {leaf} + +SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 2)); +-[ RECORD 1 ]----- +lsn | 0/1 +nsn | 0/0 +rightlink | 1 +flags | {leaf} + +SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 0)); +-[ RECORD 1 ]--------- +itemoffset | 1 +ctid | (1,65535) +itemlen | 40 +-[ RECORD 2 ]--------- +itemoffset | 2 +ctid | (2,65535) +itemlen | 40 +-[ RECORD 3 ]--------- +itemoffset | 3 +ctid | (3,65535) +itemlen | 40 +-[ RECORD 4 ]--------- +itemoffset | 4 +ctid | (4,65535) +itemlen | 40 +-[ RECORD 5 ]--------- +itemoffset | 5 +ctid | (5,65535) +itemlen | 40 +-[ RECORD 6 ]--------- +itemoffset | 6 +ctid | (6,65535) +itemlen | 40 +-[ RECORD 7 ]--------- +itemoffset | 7 +ctid | (7,65535) +itemlen | 40 + +SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 1)) LIMIT 10; +-[ RECORD 1 ]------ +itemoffset | 1 +ctid | (0,1) +itemlen | 40 +-[ RECORD 2 ]------ +itemoffset | 2 +ctid | (0,2) +itemlen | 40 +-[ RECORD 3 ]------ +itemoffset | 3 +ctid | (0,3) +itemlen | 40 +-[ RECORD 4 ]------ +itemoffset | 4 +ctid | (0,4) +itemlen | 40 +-[ RECORD 5 ]------ +itemoffset | 5 +ctid | (0,5) +itemlen | 40 +-[ RECORD 6 ]------ +itemoffset | 6 +ctid | (0,6) +itemlen | 40 +-[ RECORD 7 ]------ +itemoffset | 7 +ctid | (0,7) +itemlen | 40 +-[ RECORD 8 ]------ +itemoffset | 8 +ctid | (0,8) +itemlen | 40 +-[ RECORD 9 ]------ +itemoffset | 9 +ctid | (0,9) +itemlen | 40 +-[ RECORD 10 ]----- +itemoffset | 10 +ctid | (0,10) +itemlen | 40 + +SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 2)) LIMIT 10; +-[ RECORD 1 ]------ +itemoffset | 1 +ctid | (1,10) +itemlen | 40 +-[ RECORD 2 ]------ +itemoffset | 2 +ctid | (1,11) +itemlen | 40 +-[ RECORD 3 ]------ +itemoffset | 3 +ctid | (1,12) +itemlen | 40 +-[ RECORD 4 ]------ +itemoffset | 4 +ctid | (1,13) +itemlen | 40 +-[ RECORD 5 ]------ +itemoffset | 5 +ctid | (1,14) +itemlen | 40 +-[ RECORD 6 ]------ +itemoffset | 6 +ctid | (1,15) +itemlen | 40 +-[ RECORD 7 ]------ +itemoffset | 7 +ctid | (1,16) +itemlen | 40 +-[ RECORD 8 ]------ +itemoffset | 8 +ctid | (1,17) +itemlen | 40 +-[ RECORD 9 ]------ +itemoffset | 9 +ctid | (1,18) +itemlen | 40 +-[ RECORD 10 ]----- +itemoffset | 10 +ctid | (1,19) +itemlen | 40 + +DROP TABLE test1; diff --git a/contrib/pageinspect/gistfuncs.c b/contrib/pageinspect/gistfuncs.c new file mode 100644 index 0000000000..8517b4c241 --- /dev/null +++ b/contrib/pageinspect/gistfuncs.c @@ -0,0 +1,173 @@ +/* + * gistfuncs.c + * Functions to investigate the content of GiST indexes + * + * Copyright (c) 2014-2020, PostgreSQL Global Development Group + * + * IDENTIFICATION + * contrib/pageinspect/gitfuncs.c + */ +#include "postgres.h" + +#include "access/gist.h" +#include "access/htup.h" +#include "funcapi.h" +#include "miscadmin.h" +#include "pageinspect.h" +#include "storage/itemptr.h" +#include "utils/array.h" +#include "utils/builtins.h" +#include "utils/pg_lsn.h" + +PG_FUNCTION_INFO_V1(gist_page_opaque_info); +PG_FUNCTION_INFO_V1(gist_page_items); + +#define ItemPointerGetDatum(X) PointerGetDatum(X) + + +Datum +gist_page_opaque_info(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + TupleDesc tupdesc; + Page page; + GISTPageOpaque opaq; + HeapTuple resultTuple; + Datum values[4]; + bool nulls[4]; + Datum flags[16]; + int nflags = 0; + uint16 flagbits; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + page = get_page_from_raw(raw_page); + + opaq = (GISTPageOpaque) PageGetSpecialPointer(page); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + /* Convert the flags bitmask to an array of human-readable names */ + flagbits = opaq->flags; + if (flagbits & F_LEAF) + flags[nflags++] = CStringGetTextDatum("leaf"); + if (flagbits & F_DELETED) + flags[nflags++] = CStringGetTextDatum("deleted"); + if (flagbits & F_TUPLES_DELETED) + flags[nflags++] = CStringGetTextDatum("tuples_deleted"); + if (flagbits & F_FOLLOW_RIGHT) + flags[nflags++] = CStringGetTextDatum("follow_right"); + if (flagbits & F_HAS_GARBAGE) + flags[nflags++] = CStringGetTextDatum("has_garbage"); + flagbits &= ~(F_LEAF | F_DELETED | F_TUPLES_DELETED | F_FOLLOW_RIGHT | F_HAS_GARBAGE); + if (flagbits) + { + /* any flags we don't recognize are printed in hex */ + flags[nflags++] = DirectFunctionCall1(to_hex32, Int32GetDatum(flagbits)); + } + + memset(nulls, 0, sizeof(nulls)); + + values[0] = LSNGetDatum(PageGetLSN(page)); + values[1] = LSNGetDatum(GistPageGetNSN(page)); + values[2] = Int64GetDatum(opaq->rightlink); + values[3] = PointerGetDatum(construct_array(flags, nflags, + TEXTOID, + -1, false, TYPALIGN_INT)); + + /* Build and return the result tuple. */ + resultTuple = heap_form_tuple(tupdesc, values, nulls); + + return HeapTupleGetDatum(resultTuple); +} + +typedef struct gist_page_items_state +{ + Page page; + TupleDesc tupd; + OffsetNumber offset; +} gist_page_items_state; + +Datum +gist_page_items(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + FuncCallContext *fctx; + gist_page_items_state *inter_call_data; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + if (SRF_IS_FIRSTCALL()) + { + TupleDesc tupdesc; + MemoryContext mctx; + Page page; + + fctx = SRF_FIRSTCALL_INIT(); + mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx); + + page = get_page_from_raw(raw_page); + + inter_call_data = palloc(sizeof(gist_page_items_state)); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + inter_call_data->page = page; + inter_call_data->tupd = tupdesc; + inter_call_data->offset = FirstOffsetNumber; + + fctx->max_calls = PageGetMaxOffsetNumber(page); + fctx->user_fctx = inter_call_data; + + MemoryContextSwitchTo(mctx); + } + + fctx = SRF_PERCALL_SETUP(); + inter_call_data = fctx->user_fctx; + + if (fctx->call_cntr < fctx->max_calls) + { + Page page = inter_call_data->page; + OffsetNumber offset = inter_call_data->offset; + HeapTuple resultTuple; + Datum result; + Datum values[3]; + bool nulls[3]; + ItemId id; + IndexTuple itup; + + id = PageGetItemId(page, offset); + + if (!ItemIdIsValid(id)) + elog(ERROR, "invalid ItemId"); + + itup = (IndexTuple) PageGetItem(page, id); + + memset(nulls, 0, sizeof(nulls)); + + values[0] = DatumGetInt16(offset); + values[1] = ItemPointerGetDatum(&itup->t_tid); + values[2] = Int32GetDatum((int) IndexTupleSize(itup)); + + /* TODO: also print the keys */ + + /* Build and return the result tuple. */ + resultTuple = heap_form_tuple(inter_call_data->tupd, values, nulls); + result = HeapTupleGetDatum(resultTuple); + + inter_call_data->offset++; + SRF_RETURN_NEXT(fctx, result); + } + + SRF_RETURN_DONE(fctx); +} diff --git a/contrib/pageinspect/pageinspect--1.8--1.9.sql b/contrib/pageinspect/pageinspect--1.8--1.9.sql new file mode 100644 index 0000000000..e7a849cfed --- /dev/null +++ b/contrib/pageinspect/pageinspect--1.8--1.9.sql @@ -0,0 +1,27 @@ +/* contrib/pageinspect/pageinspect--1.8--1.9.sql */ + +-- complain if script is sourced in psql, rather than via ALTER EXTENSION +\echo Use "ALTER EXTENSION pageinspect UPDATE TO '1.9'" to load this file. \quit + +-- +-- gist_page_opaque_info() +-- +CREATE FUNCTION gist_page_opaque_info(IN page bytea, + OUT lsn pg_lsn, + OUT nsn pg_lsn, + OUT rightlink bigint, + OUT flags text[]) +AS 'MODULE_PATHNAME', 'gist_page_opaque_info' +LANGUAGE C STRICT PARALLEL SAFE; + + +-- +-- gist_page_items() +-- +CREATE FUNCTION gist_page_items(IN page bytea, + OUT itemoffset smallint, + OUT ctid tid, + OUT itemlen smallint) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'gist_page_items' +LANGUAGE C STRICT PARALLEL SAFE; diff --git a/contrib/pageinspect/pageinspect.control b/contrib/pageinspect/pageinspect.control index f8cdf526c6..bd716769a1 100644 --- a/contrib/pageinspect/pageinspect.control +++ b/contrib/pageinspect/pageinspect.control @@ -1,5 +1,5 @@ # pageinspect extension comment = 'inspect the contents of database pages at a low level' -default_version = '1.8' +default_version = '1.9' module_pathname = '$libdir/pageinspect' relocatable = true diff --git a/contrib/pageinspect/sql/gist.sql b/contrib/pageinspect/sql/gist.sql new file mode 100644 index 0000000000..12be3cd76c --- /dev/null +++ b/contrib/pageinspect/sql/gist.sql @@ -0,0 +1,15 @@ +CREATE TABLE test_gist AS SELECT point(i,i) p, i::text t FROM + generate_series(1,1000) i; +CREATE INDEX test_gist_idx ON test_gist USING gist (p); + +\x + +SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 0)); +SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 1)); +SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 2)); + +SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 0)); +SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 1)) LIMIT 10; +SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 2)) LIMIT 10; + +DROP TABLE test1; diff --git a/doc/src/sgml/pageinspect.sgml b/doc/src/sgml/pageinspect.sgml index 687c3606ba..32cfde3628 100644 --- a/doc/src/sgml/pageinspect.sgml +++ b/doc/src/sgml/pageinspect.sgml @@ -671,6 +671,66 @@ test=# SELECT first_tid, nbytes, tids[0:5] AS some_tids + + GiST Functions + + + + + gist_page_opaque_info(page bytea) returns record + + gist_page_opaque_info + + + + + + gist_page_opaque_info returns information about + a GiST index opaque area, like the NSN, rightlink and + page type. + For example: + +test=# SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 2)); + lsn | nsn | rightlink | flags +-----+-----+-----------+-------- + 0/1 | 0/0 | 1 | {leaf} +(1 row) + + + + + + + + gist_page_items(page bytea) returns setof record + + gist_page_items + + + + + + gist_page_items returns information about + the data stored in a GiST page. For example: + +test=# SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 0)); + itemoffset | ctid | itemlen +------------+-----------+--------- + 1 | (1,65535) | 40 + 2 | (2,65535) | 40 + 3 | (3,65535) | 40 + 4 | (4,65535) | 40 + 5 | (5,65535) | 40 + 6 | (6,65535) | 40 + 7 | (7,65535) | 40 +(7 rows) + + + + + + + Hash Functions -- 2.24.3 (Apple Git-128)