diff options
Diffstat (limited to 'contrib/pageinspect')
39 files changed, 5844 insertions, 0 deletions
diff --git a/contrib/pageinspect/.gitignore b/contrib/pageinspect/.gitignore new file mode 100644 index 0000000..5dcb3ff --- /dev/null +++ b/contrib/pageinspect/.gitignore @@ -0,0 +1,4 @@ +# Generated subdirectories +/log/ +/results/ +/tmp_check/ diff --git a/contrib/pageinspect/Makefile b/contrib/pageinspect/Makefile new file mode 100644 index 0000000..2d330dd --- /dev/null +++ b/contrib/pageinspect/Makefile @@ -0,0 +1,35 @@ +# contrib/pageinspect/Makefile + +MODULE_big = pageinspect +OBJS = \ + $(WIN32RES) \ + brinfuncs.o \ + btreefuncs.o \ + fsmfuncs.o \ + ginfuncs.o \ + gistfuncs.o \ + hashfuncs.o \ + heapfuncs.o \ + rawpage.o + +EXTENSION = pageinspect +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 gist hash checksum oldextversions + +ifdef USE_PGXS +PG_CONFIG = pg_config +PGXS := $(shell $(PG_CONFIG) --pgxs) +include $(PGXS) +else +subdir = contrib/pageinspect +top_builddir = ../.. +include $(top_builddir)/src/Makefile.global +include $(top_srcdir)/contrib/contrib-global.mk +endif diff --git a/contrib/pageinspect/brinfuncs.c b/contrib/pageinspect/brinfuncs.c new file mode 100644 index 0000000..2c3da71 --- /dev/null +++ b/contrib/pageinspect/brinfuncs.c @@ -0,0 +1,451 @@ +/* + * brinfuncs.c + * Functions to investigate BRIN indexes + * + * Copyright (c) 2014-2021, PostgreSQL Global Development Group + * + * IDENTIFICATION + * contrib/pageinspect/brinfuncs.c + */ +#include "postgres.h" + +#include "access/brin.h" +#include "access/brin_internal.h" +#include "access/brin_page.h" +#include "access/brin_revmap.h" +#include "access/brin_tuple.h" +#include "access/htup_details.h" +#include "catalog/index.h" +#include "catalog/pg_am_d.h" +#include "catalog/pg_type.h" +#include "funcapi.h" +#include "lib/stringinfo.h" +#include "miscadmin.h" +#include "pageinspect.h" +#include "utils/array.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" +#include "utils/rel.h" + +PG_FUNCTION_INFO_V1(brin_page_type); +PG_FUNCTION_INFO_V1(brin_page_items); +PG_FUNCTION_INFO_V1(brin_metapage_info); +PG_FUNCTION_INFO_V1(brin_revmap_data); + +#define IS_BRIN(r) ((r)->rd_rel->relam == BRIN_AM_OID) + +typedef struct brin_column_state +{ + int nstored; + FmgrInfo outputFn[FLEXIBLE_ARRAY_MEMBER]; +} brin_column_state; + + +static Page verify_brin_page(bytea *raw_page, uint16 type, + const char *strtype); + +Datum +brin_page_type(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + Page page; + char *type; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + page = get_page_from_raw(raw_page); + + if (PageIsNew(page)) + PG_RETURN_NULL(); + + /* verify the special space has the expected size */ + if (PageGetSpecialSize(page) != MAXALIGN(sizeof(BrinSpecialSpace))) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a valid %s page", "BRIN"), + errdetail("Expected special size %d, got %d.", + (int) MAXALIGN(sizeof(BrinSpecialSpace)), + (int) PageGetSpecialSize(page)))); + + switch (BrinPageType(page)) + { + case BRIN_PAGETYPE_META: + type = "meta"; + break; + case BRIN_PAGETYPE_REVMAP: + type = "revmap"; + break; + case BRIN_PAGETYPE_REGULAR: + type = "regular"; + break; + default: + type = psprintf("unknown (%02x)", BrinPageType(page)); + break; + } + + PG_RETURN_TEXT_P(cstring_to_text(type)); +} + +/* + * Verify that the given bytea contains a BRIN page of the indicated page + * type, or die in the attempt. A pointer to the page is returned. + */ +static Page +verify_brin_page(bytea *raw_page, uint16 type, const char *strtype) +{ + Page page = get_page_from_raw(raw_page); + + if (PageIsNew(page)) + return page; + + /* verify the special space has the expected size */ + if (PageGetSpecialSize(page) != MAXALIGN(sizeof(BrinSpecialSpace))) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a valid %s page", "BRIN"), + errdetail("Expected special size %d, got %d.", + (int) MAXALIGN(sizeof(BrinSpecialSpace)), + (int) PageGetSpecialSize(page)))); + + /* verify the special space says this page is what we want */ + if (BrinPageType(page) != type) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("page is not a BRIN page of type \"%s\"", strtype), + errdetail("Expected special type %08x, got %08x.", + type, BrinPageType(page)))); + + return page; +} + + +/* + * Extract all item values from a BRIN index page + * + * Usage: SELECT * FROM brin_page_items(get_raw_page('idx', 1), 'idx'::regclass); + */ +Datum +brin_page_items(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + Oid indexRelid = PG_GETARG_OID(1); + ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; + TupleDesc tupdesc; + MemoryContext oldcontext; + Tuplestorestate *tupstore; + Relation indexRel; + brin_column_state **columns; + BrinDesc *bdesc; + BrinMemTuple *dtup; + Page page; + OffsetNumber offset; + AttrNumber attno; + bool unusedItem; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + /* check to see if caller supports us returning a tuplestore */ + if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("set-valued function called in context that cannot accept a set"))); + if (!(rsinfo->allowedModes & SFRM_Materialize) || + rsinfo->expectedDesc == NULL) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("materialize mode required, but it is not allowed in this context"))); + + /* 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"); + + /* Build tuplestore to hold the result rows */ + oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); + + tupstore = tuplestore_begin_heap(true, false, work_mem); + rsinfo->returnMode = SFRM_Materialize; + rsinfo->setResult = tupstore; + rsinfo->setDesc = tupdesc; + + MemoryContextSwitchTo(oldcontext); + + indexRel = index_open(indexRelid, AccessShareLock); + + if (!IS_BRIN(indexRel)) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("\"%s\" is not a %s index", + RelationGetRelationName(indexRel), "BRIN"))); + + bdesc = brin_build_desc(indexRel); + + /* minimally verify the page we got */ + page = verify_brin_page(raw_page, BRIN_PAGETYPE_REGULAR, "regular"); + + if (PageIsNew(page)) + { + brin_free_desc(bdesc); + index_close(indexRel, AccessShareLock); + PG_RETURN_NULL(); + } + + /* + * Initialize output functions for all indexed datatypes; simplifies + * calling them later. + */ + columns = palloc(sizeof(brin_column_state *) * RelationGetDescr(indexRel)->natts); + for (attno = 1; attno <= bdesc->bd_tupdesc->natts; attno++) + { + Oid output; + bool isVarlena; + BrinOpcInfo *opcinfo; + int i; + brin_column_state *column; + + opcinfo = bdesc->bd_info[attno - 1]; + column = palloc(offsetof(brin_column_state, outputFn) + + sizeof(FmgrInfo) * opcinfo->oi_nstored); + + column->nstored = opcinfo->oi_nstored; + for (i = 0; i < opcinfo->oi_nstored; i++) + { + getTypeOutputInfo(opcinfo->oi_typcache[i]->type_id, &output, &isVarlena); + fmgr_info(output, &column->outputFn[i]); + } + + columns[attno - 1] = column; + } + + offset = FirstOffsetNumber; + unusedItem = false; + dtup = NULL; + for (;;) + { + Datum values[7]; + bool nulls[7]; + + /* + * This loop is called once for every attribute of every tuple in the + * page. At the start of a tuple, we get a NULL dtup; that's our + * signal for obtaining and decoding the next one. If that's not the + * case, we output the next attribute. + */ + if (dtup == NULL) + { + ItemId itemId; + + /* verify item status: if there's no data, we can't decode */ + itemId = PageGetItemId(page, offset); + if (ItemIdIsUsed(itemId)) + { + dtup = brin_deform_tuple(bdesc, + (BrinTuple *) PageGetItem(page, itemId), + NULL); + attno = 1; + unusedItem = false; + } + else + unusedItem = true; + } + else + attno++; + + MemSet(nulls, 0, sizeof(nulls)); + + if (unusedItem) + { + values[0] = UInt16GetDatum(offset); + nulls[1] = true; + nulls[2] = true; + nulls[3] = true; + nulls[4] = true; + nulls[5] = true; + nulls[6] = true; + } + else + { + int att = attno - 1; + + values[0] = UInt16GetDatum(offset); + switch (TupleDescAttr(tupdesc, 1)->atttypid) + { + case INT8OID: + values[1] = Int64GetDatum((int64) dtup->bt_blkno); + break; + case INT4OID: + /* support for old extension version */ + values[1] = UInt32GetDatum(dtup->bt_blkno); + break; + default: + elog(ERROR, "incorrect output types"); + } + values[2] = UInt16GetDatum(attno); + values[3] = BoolGetDatum(dtup->bt_columns[att].bv_allnulls); + values[4] = BoolGetDatum(dtup->bt_columns[att].bv_hasnulls); + values[5] = BoolGetDatum(dtup->bt_placeholder); + if (!dtup->bt_columns[att].bv_allnulls) + { + BrinValues *bvalues = &dtup->bt_columns[att]; + StringInfoData s; + bool first; + int i; + + initStringInfo(&s); + appendStringInfoChar(&s, '{'); + + first = true; + for (i = 0; i < columns[att]->nstored; i++) + { + char *val; + + if (!first) + appendStringInfoString(&s, " .. "); + first = false; + val = OutputFunctionCall(&columns[att]->outputFn[i], + bvalues->bv_values[i]); + appendStringInfoString(&s, val); + pfree(val); + } + appendStringInfoChar(&s, '}'); + + values[6] = CStringGetTextDatum(s.data); + pfree(s.data); + } + else + { + nulls[6] = true; + } + } + + tuplestore_putvalues(tupstore, tupdesc, values, nulls); + + /* + * If the item was unused, jump straight to the next one; otherwise, + * the only cleanup needed here is to set our signal to go to the next + * tuple in the following iteration, by freeing the current one. + */ + if (unusedItem) + offset = OffsetNumberNext(offset); + else if (attno >= bdesc->bd_tupdesc->natts) + { + pfree(dtup); + dtup = NULL; + offset = OffsetNumberNext(offset); + } + + /* + * If we're beyond the end of the page, we're done. + */ + if (offset > PageGetMaxOffsetNumber(page)) + break; + } + + /* clean up and return the tuplestore */ + brin_free_desc(bdesc); + tuplestore_donestoring(tupstore); + index_close(indexRel, AccessShareLock); + + return (Datum) 0; +} + +Datum +brin_metapage_info(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + Page page; + BrinMetaPageData *meta; + TupleDesc tupdesc; + Datum values[4]; + bool nulls[4]; + HeapTuple htup; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + page = verify_brin_page(raw_page, BRIN_PAGETYPE_META, "metapage"); + + if (PageIsNew(page)) + PG_RETURN_NULL(); + + /* 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"); + tupdesc = BlessTupleDesc(tupdesc); + + /* Extract values from the metapage */ + meta = (BrinMetaPageData *) PageGetContents(page); + MemSet(nulls, 0, sizeof(nulls)); + values[0] = CStringGetTextDatum(psprintf("0x%08X", meta->brinMagic)); + values[1] = Int32GetDatum(meta->brinVersion); + values[2] = Int32GetDatum(meta->pagesPerRange); + values[3] = Int64GetDatum(meta->lastRevmapPage); + + htup = heap_form_tuple(tupdesc, values, nulls); + + PG_RETURN_DATUM(HeapTupleGetDatum(htup)); +} + +/* + * Return the TID array stored in a BRIN revmap page + */ +Datum +brin_revmap_data(PG_FUNCTION_ARGS) +{ + struct + { + ItemPointerData *tids; + int idx; + } *state; + FuncCallContext *fctx; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + if (SRF_IS_FIRSTCALL()) + { + bytea *raw_page = PG_GETARG_BYTEA_P(0); + MemoryContext mctx; + Page page; + + /* create a function context for cross-call persistence */ + fctx = SRF_FIRSTCALL_INIT(); + + /* switch to memory context appropriate for multiple function calls */ + mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx); + + /* minimally verify the page we got */ + page = verify_brin_page(raw_page, BRIN_PAGETYPE_REVMAP, "revmap"); + + if (PageIsNew(page)) + { + MemoryContextSwitchTo(mctx); + PG_RETURN_NULL(); + } + + state = palloc(sizeof(*state)); + state->tids = ((RevmapContents *) PageGetContents(page))->rm_tids; + state->idx = 0; + + fctx->user_fctx = state; + + MemoryContextSwitchTo(mctx); + } + + fctx = SRF_PERCALL_SETUP(); + state = fctx->user_fctx; + + if (state->idx < REVMAP_PAGE_MAXITEMS) + SRF_RETURN_NEXT(fctx, PointerGetDatum(&state->tids[state->idx++])); + + SRF_RETURN_DONE(fctx); +} diff --git a/contrib/pageinspect/btreefuncs.c b/contrib/pageinspect/btreefuncs.c new file mode 100644 index 0000000..2044b88 --- /dev/null +++ b/contrib/pageinspect/btreefuncs.c @@ -0,0 +1,793 @@ +/* + * contrib/pageinspect/btreefuncs.c + * + * + * btreefuncs.c + * + * Copyright (c) 2006 Satoshi Nagayasu <nagayasus@nttdata.co.jp> + * + * Permission to use, copy, modify, and distribute this software and + * its documentation for any purpose, without fee, and without a + * written agreement is hereby granted, provided that the above + * copyright notice and this paragraph and the following two + * paragraphs appear in all copies. + * + * IN NO EVENT SHALL THE AUTHOR BE LIABLE TO ANY PARTY FOR DIRECT, + * INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, INCLUDING + * LOST PROFITS, ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS + * DOCUMENTATION, EVEN IF THE UNIVERSITY OF CALIFORNIA HAS BEEN ADVISED + * OF THE POSSIBILITY OF SUCH DAMAGE. + * + * THE AUTHOR SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE. THE SOFTWARE PROVIDED HEREUNDER IS ON AN "AS + * IS" BASIS, AND THE AUTHOR HAS NO OBLIGATIONS TO PROVIDE MAINTENANCE, + * SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS. + */ + +#include "postgres.h" + +#include "access/nbtree.h" +#include "access/relation.h" +#include "catalog/namespace.h" +#include "catalog/pg_am.h" +#include "catalog/pg_type.h" +#include "funcapi.h" +#include "miscadmin.h" +#include "pageinspect.h" +#include "utils/array.h" +#include "utils/builtins.h" +#include "utils/rel.h" +#include "utils/varlena.h" + +PG_FUNCTION_INFO_V1(bt_metap); +PG_FUNCTION_INFO_V1(bt_page_items_1_9); +PG_FUNCTION_INFO_V1(bt_page_items); +PG_FUNCTION_INFO_V1(bt_page_items_bytea); +PG_FUNCTION_INFO_V1(bt_page_stats_1_9); +PG_FUNCTION_INFO_V1(bt_page_stats); + +#define IS_INDEX(r) ((r)->rd_rel->relkind == RELKIND_INDEX) +#define IS_BTREE(r) ((r)->rd_rel->relam == BTREE_AM_OID) +#define DatumGetItemPointer(X) ((ItemPointer) DatumGetPointer(X)) +#define ItemPointerGetDatum(X) PointerGetDatum(X) + +/* note: BlockNumber is unsigned, hence can't be negative */ +#define CHECK_RELATION_BLOCK_RANGE(rel, blkno) { \ + if ( RelationGetNumberOfBlocks(rel) <= (BlockNumber) (blkno) ) \ + elog(ERROR, "block number out of range"); } + +/* ------------------------------------------------ + * structure for single btree page statistics + * ------------------------------------------------ + */ +typedef struct BTPageStat +{ + uint32 blkno; + uint32 live_items; + uint32 dead_items; + uint32 page_size; + uint32 max_avail; + uint32 free_size; + uint32 avg_item_size; + char type; + + /* opaque data */ + BlockNumber btpo_prev; + BlockNumber btpo_next; + uint32 btpo_level; + uint16 btpo_flags; + BTCycleId btpo_cycleid; +} BTPageStat; + + +/* ------------------------------------------------- + * GetBTPageStatistics() + * + * Collect statistics of single b-tree page + * ------------------------------------------------- + */ +static void +GetBTPageStatistics(BlockNumber blkno, Buffer buffer, BTPageStat *stat) +{ + Page page = BufferGetPage(buffer); + PageHeader phdr = (PageHeader) page; + OffsetNumber maxoff = PageGetMaxOffsetNumber(page); + BTPageOpaque opaque = (BTPageOpaque) PageGetSpecialPointer(page); + int item_size = 0; + int off; + + stat->blkno = blkno; + + stat->max_avail = BLCKSZ - (BLCKSZ - phdr->pd_special + SizeOfPageHeaderData); + + stat->dead_items = stat->live_items = 0; + + stat->page_size = PageGetPageSize(page); + + /* page type (flags) */ + if (P_ISDELETED(opaque)) + { + /* We divide deleted pages into leaf ('d') or internal ('D') */ + if (P_ISLEAF(opaque) || !P_HAS_FULLXID(opaque)) + stat->type = 'd'; + else + stat->type = 'D'; + + /* + * Report safexid in a deleted page. + * + * Handle pg_upgrade'd deleted pages that used the previous safexid + * representation in btpo_level field (this used to be a union type + * called "bpto"). + */ + if (P_HAS_FULLXID(opaque)) + { + FullTransactionId safexid = BTPageGetDeleteXid(page); + + elog(DEBUG2, "deleted page from block %u has safexid %u:%u", + blkno, EpochFromFullTransactionId(safexid), + XidFromFullTransactionId(safexid)); + } + else + elog(DEBUG2, "deleted page from block %u has safexid %u", + blkno, opaque->btpo_level); + + /* Don't interpret BTDeletedPageData as index tuples */ + maxoff = InvalidOffsetNumber; + } + else if (P_IGNORE(opaque)) + stat->type = 'e'; + else if (P_ISLEAF(opaque)) + stat->type = 'l'; + else if (P_ISROOT(opaque)) + stat->type = 'r'; + else + stat->type = 'i'; + + /* btpage opaque data */ + stat->btpo_prev = opaque->btpo_prev; + stat->btpo_next = opaque->btpo_next; + stat->btpo_level = opaque->btpo_level; + stat->btpo_flags = opaque->btpo_flags; + stat->btpo_cycleid = opaque->btpo_cycleid; + + /* count live and dead tuples, and free space */ + for (off = FirstOffsetNumber; off <= maxoff; off++) + { + IndexTuple itup; + + ItemId id = PageGetItemId(page, off); + + itup = (IndexTuple) PageGetItem(page, id); + + item_size += IndexTupleSize(itup); + + if (!ItemIdIsDead(id)) + stat->live_items++; + else + stat->dead_items++; + } + stat->free_size = PageGetFreeSpace(page); + + if ((stat->live_items + stat->dead_items) > 0) + stat->avg_item_size = item_size / (stat->live_items + stat->dead_items); + else + stat->avg_item_size = 0; +} + +/* ----------------------------------------------- + * bt_page_stats() + * + * Usage: SELECT * FROM bt_page_stats('t1_pkey', 1); + * ----------------------------------------------- + */ +static Datum +bt_page_stats_internal(PG_FUNCTION_ARGS, enum pageinspect_version ext_version) +{ + text *relname = PG_GETARG_TEXT_PP(0); + int64 blkno = (ext_version == PAGEINSPECT_V1_8 ? PG_GETARG_UINT32(1) : PG_GETARG_INT64(1)); + Buffer buffer; + Relation rel; + RangeVar *relrv; + Datum result; + HeapTuple tuple; + TupleDesc tupleDesc; + int j; + char *values[11]; + BTPageStat stat; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use pageinspect functions"))); + + relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); + rel = relation_openrv(relrv, AccessShareLock); + + if (!IS_INDEX(rel) || !IS_BTREE(rel)) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("\"%s\" is not a %s index", + RelationGetRelationName(rel), "btree"))); + + /* + * Reject attempts to read non-local temporary relations; we would be + * likely to get wrong data since we have no visibility into the owning + * session's local buffers. + */ + if (RELATION_IS_OTHER_TEMP(rel)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot access temporary tables of other sessions"))); + + if (blkno < 0 || blkno > MaxBlockNumber) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid block number"))); + + if (blkno == 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("block 0 is a meta page"))); + + CHECK_RELATION_BLOCK_RANGE(rel, blkno); + + buffer = ReadBuffer(rel, blkno); + LockBuffer(buffer, BUFFER_LOCK_SHARE); + + /* keep compiler quiet */ + stat.btpo_prev = stat.btpo_next = InvalidBlockNumber; + stat.btpo_flags = stat.free_size = stat.avg_item_size = 0; + + GetBTPageStatistics(blkno, buffer, &stat); + + UnlockReleaseBuffer(buffer); + relation_close(rel, AccessShareLock); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + j = 0; + values[j++] = psprintf("%u", stat.blkno); + values[j++] = psprintf("%c", stat.type); + values[j++] = psprintf("%u", stat.live_items); + values[j++] = psprintf("%u", stat.dead_items); + values[j++] = psprintf("%u", stat.avg_item_size); + values[j++] = psprintf("%u", stat.page_size); + values[j++] = psprintf("%u", stat.free_size); + values[j++] = psprintf("%u", stat.btpo_prev); + values[j++] = psprintf("%u", stat.btpo_next); + values[j++] = psprintf("%u", stat.btpo_level); + values[j++] = psprintf("%d", stat.btpo_flags); + + tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc), + values); + + result = HeapTupleGetDatum(tuple); + + PG_RETURN_DATUM(result); +} + +Datum +bt_page_stats_1_9(PG_FUNCTION_ARGS) +{ + return bt_page_stats_internal(fcinfo, PAGEINSPECT_V1_9); +} + +/* entry point for old extension version */ +Datum +bt_page_stats(PG_FUNCTION_ARGS) +{ + return bt_page_stats_internal(fcinfo, PAGEINSPECT_V1_8); +} + + +/* + * cross-call data structure for SRF + */ +struct user_args +{ + Page page; + OffsetNumber offset; + bool leafpage; + bool rightmost; + TupleDesc tupd; +}; + +/*------------------------------------------------------- + * bt_page_print_tuples() + * + * Form a tuple describing index tuple at a given offset + * ------------------------------------------------------ + */ +static Datum +bt_page_print_tuples(struct user_args *uargs) +{ + Page page = uargs->page; + OffsetNumber offset = uargs->offset; + bool leafpage = uargs->leafpage; + bool rightmost = uargs->rightmost; + bool ispivottuple; + Datum values[9]; + bool nulls[9]; + HeapTuple tuple; + ItemId id; + IndexTuple itup; + int j; + int off; + int dlen; + char *dump, + *datacstring; + char *ptr; + ItemPointer htid; + + id = PageGetItemId(page, offset); + + if (!ItemIdIsValid(id)) + elog(ERROR, "invalid ItemId"); + + itup = (IndexTuple) PageGetItem(page, id); + + j = 0; + memset(nulls, 0, sizeof(nulls)); + values[j++] = DatumGetInt16(offset); + values[j++] = ItemPointerGetDatum(&itup->t_tid); + values[j++] = Int32GetDatum((int) IndexTupleSize(itup)); + values[j++] = BoolGetDatum(IndexTupleHasNulls(itup)); + values[j++] = BoolGetDatum(IndexTupleHasVarwidths(itup)); + + ptr = (char *) itup + IndexInfoFindDataOffset(itup->t_info); + dlen = IndexTupleSize(itup) - IndexInfoFindDataOffset(itup->t_info); + + /* + * Make sure that "data" column does not include posting list or pivot + * tuple representation of heap TID(s). + * + * Note: BTreeTupleIsPivot() won't work reliably on !heapkeyspace indexes + * (those built before BTREE_VERSION 4), but we have no way of determining + * if this page came from a !heapkeyspace index. We may only have a bytea + * nbtree page image to go on, so in general there is no metapage that we + * can check. + * + * That's okay here because BTreeTupleIsPivot() can only return false for + * a !heapkeyspace pivot, never true for a !heapkeyspace non-pivot. Since + * heap TID isn't part of the keyspace in a !heapkeyspace index anyway, + * there cannot possibly be a pivot tuple heap TID representation that we + * fail to make an adjustment for. A !heapkeyspace index can have + * BTreeTupleIsPivot() return true (due to things like suffix truncation + * for INCLUDE indexes in Postgres v11), but when that happens + * BTreeTupleGetHeapTID() can be trusted to work reliably (i.e. return + * NULL). + * + * Note: BTreeTupleIsPosting() always works reliably, even with + * !heapkeyspace indexes. + */ + if (BTreeTupleIsPosting(itup)) + dlen -= IndexTupleSize(itup) - BTreeTupleGetPostingOffset(itup); + else if (BTreeTupleIsPivot(itup) && BTreeTupleGetHeapTID(itup) != NULL) + dlen -= MAXALIGN(sizeof(ItemPointerData)); + + if (dlen < 0 || dlen > INDEX_SIZE_MASK) + elog(ERROR, "invalid tuple length %d for tuple at offset number %u", + dlen, offset); + dump = palloc0(dlen * 3 + 1); + datacstring = dump; + for (off = 0; off < dlen; off++) + { + if (off > 0) + *dump++ = ' '; + sprintf(dump, "%02x", *(ptr + off) & 0xff); + dump += 2; + } + values[j++] = CStringGetTextDatum(datacstring); + pfree(datacstring); + + /* + * We need to work around the BTreeTupleIsPivot() !heapkeyspace limitation + * again. Deduce whether or not tuple must be a pivot tuple based on + * whether or not the page is a leaf page, as well as the page offset + * number of the tuple. + */ + ispivottuple = (!leafpage || (!rightmost && offset == P_HIKEY)); + + /* LP_DEAD bit can never be set for pivot tuples, so show a NULL there */ + if (!ispivottuple) + values[j++] = BoolGetDatum(ItemIdIsDead(id)); + else + { + Assert(!ItemIdIsDead(id)); + nulls[j++] = true; + } + + htid = BTreeTupleGetHeapTID(itup); + if (ispivottuple && !BTreeTupleIsPivot(itup)) + { + /* Don't show bogus heap TID in !heapkeyspace pivot tuple */ + htid = NULL; + } + + if (htid) + values[j++] = ItemPointerGetDatum(htid); + else + nulls[j++] = true; + + if (BTreeTupleIsPosting(itup)) + { + /* Build an array of item pointers */ + ItemPointer tids; + Datum *tids_datum; + int nposting; + + tids = BTreeTupleGetPosting(itup); + nposting = BTreeTupleGetNPosting(itup); + tids_datum = (Datum *) palloc(nposting * sizeof(Datum)); + for (int i = 0; i < nposting; i++) + tids_datum[i] = ItemPointerGetDatum(&tids[i]); + values[j++] = PointerGetDatum(construct_array(tids_datum, + nposting, + TIDOID, + sizeof(ItemPointerData), + false, TYPALIGN_SHORT)); + pfree(tids_datum); + } + else + nulls[j++] = true; + + /* Build and return the result tuple */ + tuple = heap_form_tuple(uargs->tupd, values, nulls); + + return HeapTupleGetDatum(tuple); +} + +/*------------------------------------------------------- + * bt_page_items() + * + * Get IndexTupleData set in a btree page + * + * Usage: SELECT * FROM bt_page_items('t1_pkey', 1); + *------------------------------------------------------- + */ +static Datum +bt_page_items_internal(PG_FUNCTION_ARGS, enum pageinspect_version ext_version) +{ + text *relname = PG_GETARG_TEXT_PP(0); + int64 blkno = (ext_version == PAGEINSPECT_V1_8 ? PG_GETARG_UINT32(1) : PG_GETARG_INT64(1)); + Datum result; + FuncCallContext *fctx; + MemoryContext mctx; + struct user_args *uargs; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use pageinspect functions"))); + + if (SRF_IS_FIRSTCALL()) + { + RangeVar *relrv; + Relation rel; + Buffer buffer; + BTPageOpaque opaque; + TupleDesc tupleDesc; + + fctx = SRF_FIRSTCALL_INIT(); + + relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); + rel = relation_openrv(relrv, AccessShareLock); + + if (!IS_INDEX(rel) || !IS_BTREE(rel)) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("\"%s\" is not a %s index", + RelationGetRelationName(rel), "btree"))); + + /* + * Reject attempts to read non-local temporary relations; we would be + * likely to get wrong data since we have no visibility into the + * owning session's local buffers. + */ + if (RELATION_IS_OTHER_TEMP(rel)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot access temporary tables of other sessions"))); + + if (blkno < 0 || blkno > MaxBlockNumber) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid block number"))); + + if (blkno == 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("block 0 is a meta page"))); + + CHECK_RELATION_BLOCK_RANGE(rel, blkno); + + buffer = ReadBuffer(rel, blkno); + LockBuffer(buffer, BUFFER_LOCK_SHARE); + + /* + * We copy the page into local storage to avoid holding pin on the + * buffer longer than we must, and possibly failing to release it at + * all if the calling query doesn't fetch all rows. + */ + mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx); + + uargs = palloc(sizeof(struct user_args)); + + uargs->page = palloc(BLCKSZ); + memcpy(uargs->page, BufferGetPage(buffer), BLCKSZ); + + UnlockReleaseBuffer(buffer); + relation_close(rel, AccessShareLock); + + uargs->offset = FirstOffsetNumber; + + opaque = (BTPageOpaque) PageGetSpecialPointer(uargs->page); + + if (!P_ISDELETED(opaque)) + fctx->max_calls = PageGetMaxOffsetNumber(uargs->page); + else + { + /* Don't interpret BTDeletedPageData as index tuples */ + elog(NOTICE, "page from block " INT64_FORMAT " is deleted", blkno); + fctx->max_calls = 0; + } + uargs->leafpage = P_ISLEAF(opaque); + uargs->rightmost = P_RIGHTMOST(opaque); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + tupleDesc = BlessTupleDesc(tupleDesc); + + uargs->tupd = tupleDesc; + + fctx->user_fctx = uargs; + + MemoryContextSwitchTo(mctx); + } + + fctx = SRF_PERCALL_SETUP(); + uargs = fctx->user_fctx; + + if (fctx->call_cntr < fctx->max_calls) + { + result = bt_page_print_tuples(uargs); + uargs->offset++; + SRF_RETURN_NEXT(fctx, result); + } + + SRF_RETURN_DONE(fctx); +} + +Datum +bt_page_items_1_9(PG_FUNCTION_ARGS) +{ + return bt_page_items_internal(fcinfo, PAGEINSPECT_V1_9); +} + +/* entry point for old extension version */ +Datum +bt_page_items(PG_FUNCTION_ARGS) +{ + return bt_page_items_internal(fcinfo, PAGEINSPECT_V1_8); +} + +/*------------------------------------------------------- + * bt_page_items_bytea() + * + * Get IndexTupleData set in a btree page + * + * Usage: SELECT * FROM bt_page_items(get_raw_page('t1_pkey', 1)); + *------------------------------------------------------- + */ + +Datum +bt_page_items_bytea(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + Datum result; + FuncCallContext *fctx; + struct user_args *uargs; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + if (SRF_IS_FIRSTCALL()) + { + BTPageOpaque opaque; + MemoryContext mctx; + TupleDesc tupleDesc; + + fctx = SRF_FIRSTCALL_INIT(); + mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx); + + uargs = palloc(sizeof(struct user_args)); + + uargs->page = get_page_from_raw(raw_page); + + if (PageIsNew(uargs->page)) + { + MemoryContextSwitchTo(mctx); + PG_RETURN_NULL(); + } + + uargs->offset = FirstOffsetNumber; + + /* verify the special space has the expected size */ + if (PageGetSpecialSize(uargs->page) != MAXALIGN(sizeof(BTPageOpaqueData))) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a valid %s page", "btree"), + errdetail("Expected special size %d, got %d.", + (int) MAXALIGN(sizeof(BTPageOpaqueData)), + (int) PageGetSpecialSize(uargs->page)))); + + opaque = (BTPageOpaque) PageGetSpecialPointer(uargs->page); + + if (P_ISMETA(opaque)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("block is a meta page"))); + + if (P_ISLEAF(opaque) && opaque->btpo_level != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("block is not a valid btree leaf page"))); + + if (P_ISDELETED(opaque)) + elog(NOTICE, "page is deleted"); + + if (!P_ISDELETED(opaque)) + fctx->max_calls = PageGetMaxOffsetNumber(uargs->page); + else + { + /* Don't interpret BTDeletedPageData as index tuples */ + elog(NOTICE, "page from block is deleted"); + fctx->max_calls = 0; + } + uargs->leafpage = P_ISLEAF(opaque); + uargs->rightmost = P_RIGHTMOST(opaque); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + tupleDesc = BlessTupleDesc(tupleDesc); + + uargs->tupd = tupleDesc; + + fctx->user_fctx = uargs; + + MemoryContextSwitchTo(mctx); + } + + fctx = SRF_PERCALL_SETUP(); + uargs = fctx->user_fctx; + + if (fctx->call_cntr < fctx->max_calls) + { + result = bt_page_print_tuples(uargs); + uargs->offset++; + SRF_RETURN_NEXT(fctx, result); + } + + SRF_RETURN_DONE(fctx); +} + +/* Number of output arguments (columns) for bt_metap() */ +#define BT_METAP_COLS_V1_8 9 + +/* ------------------------------------------------ + * bt_metap() + * + * Get a btree's meta-page information + * + * Usage: SELECT * FROM bt_metap('t1_pkey') + * ------------------------------------------------ + */ +Datum +bt_metap(PG_FUNCTION_ARGS) +{ + text *relname = PG_GETARG_TEXT_PP(0); + Datum result; + Relation rel; + RangeVar *relrv; + BTMetaPageData *metad; + TupleDesc tupleDesc; + int j; + char *values[9]; + Buffer buffer; + Page page; + HeapTuple tuple; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use pageinspect functions"))); + + relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); + rel = relation_openrv(relrv, AccessShareLock); + + if (!IS_INDEX(rel) || !IS_BTREE(rel)) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("\"%s\" is not a %s index", + RelationGetRelationName(rel), "btree"))); + + /* + * Reject attempts to read non-local temporary relations; we would be + * likely to get wrong data since we have no visibility into the owning + * session's local buffers. + */ + if (RELATION_IS_OTHER_TEMP(rel)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot access temporary tables of other sessions"))); + + buffer = ReadBuffer(rel, 0); + LockBuffer(buffer, BUFFER_LOCK_SHARE); + + page = BufferGetPage(buffer); + metad = BTPageGetMeta(page); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + /* + * We need a kluge here to detect API versions prior to 1.8. Earlier + * versions incorrectly used int4 for certain columns. + * + * There is no way to reliably avoid the problems created by the old + * function definition at this point, so insist that the user update the + * extension. + */ + if (tupleDesc->natts < BT_METAP_COLS_V1_8) + ereport(ERROR, + (errcode(ERRCODE_INVALID_FUNCTION_DEFINITION), + errmsg("function has wrong number of declared columns"), + errhint("To resolve the problem, update the \"pageinspect\" extension to the latest version."))); + + j = 0; + values[j++] = psprintf("%d", metad->btm_magic); + values[j++] = psprintf("%d", metad->btm_version); + values[j++] = psprintf(INT64_FORMAT, (int64) metad->btm_root); + values[j++] = psprintf(INT64_FORMAT, (int64) metad->btm_level); + values[j++] = psprintf(INT64_FORMAT, (int64) metad->btm_fastroot); + values[j++] = psprintf(INT64_FORMAT, (int64) metad->btm_fastlevel); + + /* + * Get values of extended metadata if available, use default values + * otherwise. Note that we rely on the assumption that btm_allequalimage + * is initialized to zero with indexes that were built on versions prior + * to Postgres 13 (just like _bt_metaversion()). + */ + if (metad->btm_version >= BTREE_NOVAC_VERSION) + { + values[j++] = psprintf(INT64_FORMAT, + (int64) metad->btm_last_cleanup_num_delpages); + values[j++] = psprintf("%f", metad->btm_last_cleanup_num_heap_tuples); + values[j++] = metad->btm_allequalimage ? "t" : "f"; + } + else + { + values[j++] = "0"; + values[j++] = "-1"; + values[j++] = "f"; + } + + tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc), + values); + + result = HeapTupleGetDatum(tuple); + + UnlockReleaseBuffer(buffer); + relation_close(rel, AccessShareLock); + + PG_RETURN_DATUM(result); +} diff --git a/contrib/pageinspect/expected/brin.out b/contrib/pageinspect/expected/brin.out new file mode 100644 index 0000000..d19cdc3 --- /dev/null +++ b/contrib/pageinspect/expected/brin.out @@ -0,0 +1,90 @@ +CREATE TABLE test1 (a int, b text); +INSERT INTO test1 VALUES (1, 'one'); +CREATE INDEX test1_a_idx ON test1 USING brin (a); +SELECT brin_page_type(get_raw_page('test1_a_idx', 0)); + brin_page_type +---------------- + meta +(1 row) + +SELECT brin_page_type(get_raw_page('test1_a_idx', 1)); + brin_page_type +---------------- + revmap +(1 row) + +SELECT brin_page_type(get_raw_page('test1_a_idx', 2)); + brin_page_type +---------------- + regular +(1 row) + +SELECT * FROM brin_metapage_info(get_raw_page('test1_a_idx', 0)); + magic | version | pagesperrange | lastrevmappage +------------+---------+---------------+---------------- + 0xA8109CFA | 1 | 128 | 1 +(1 row) + +SELECT * FROM brin_metapage_info(get_raw_page('test1_a_idx', 1)); +ERROR: page is not a BRIN page of type "metapage" +DETAIL: Expected special type 0000f091, got 0000f092. +SELECT * FROM brin_revmap_data(get_raw_page('test1_a_idx', 0)) LIMIT 5; +ERROR: page is not a BRIN page of type "revmap" +DETAIL: Expected special type 0000f092, got 0000f091. +SELECT * FROM brin_revmap_data(get_raw_page('test1_a_idx', 1)) LIMIT 5; + pages +------- + (2,1) + (0,0) + (0,0) + (0,0) + (0,0) +(5 rows) + +SELECT * FROM brin_page_items(get_raw_page('test1_a_idx', 2), 'test1_a_idx') + ORDER BY blknum, attnum LIMIT 5; + itemoffset | blknum | attnum | allnulls | hasnulls | placeholder | value +------------+--------+--------+----------+----------+-------------+---------- + 1 | 0 | 1 | f | f | f | {1 .. 1} +(1 row) + +-- Failure for non-BRIN index. +CREATE INDEX test1_a_btree ON test1 (a); +SELECT brin_page_items(get_raw_page('test1_a_btree', 0), 'test1_a_btree'); +ERROR: "test1_a_btree" is not a BRIN index +-- Mask DETAIL messages as these are not portable across architectures. +\set VERBOSITY terse +-- Invalid special area size +SELECT brin_page_type(get_raw_page('test1', 0)); +ERROR: input page is not a valid BRIN page +SELECT * FROM brin_metapage_info(get_raw_page('test1', 0)); +ERROR: input page is not a valid BRIN page +SELECT * FROM brin_revmap_data(get_raw_page('test1', 0)); +ERROR: input page is not a valid BRIN page +\set VERBOSITY default +-- Tests with all-zero pages. +SHOW block_size \gset +SELECT brin_page_type(decode(repeat('00', :block_size), 'hex')); + brin_page_type +---------------- + +(1 row) + +SELECT brin_page_items(decode(repeat('00', :block_size), 'hex'), 'test1_a_idx'); + brin_page_items +----------------- +(0 rows) + +SELECT brin_metapage_info(decode(repeat('00', :block_size), 'hex')); + brin_metapage_info +-------------------- + +(1 row) + +SELECT brin_revmap_data(decode(repeat('00', :block_size), 'hex')); + brin_revmap_data +------------------ + +(1 row) + +DROP TABLE test1; diff --git a/contrib/pageinspect/expected/btree.out b/contrib/pageinspect/expected/btree.out new file mode 100644 index 0000000..035a81a --- /dev/null +++ b/contrib/pageinspect/expected/btree.out @@ -0,0 +1,108 @@ +CREATE TABLE test1 (a int8, b int4range); +INSERT INTO test1 VALUES (72057594037927937, '[0,1)'); +CREATE INDEX test1_a_idx ON test1 USING btree (a); +\x +SELECT * FROM bt_metap('test1_a_idx'); +-[ RECORD 1 ]-------------+------- +magic | 340322 +version | 4 +root | 1 +level | 0 +fastroot | 1 +fastlevel | 0 +last_cleanup_num_delpages | 0 +last_cleanup_num_tuples | -1 +allequalimage | t + +SELECT * FROM bt_page_stats('test1_a_idx', -1); +ERROR: invalid block number +SELECT * FROM bt_page_stats('test1_a_idx', 0); +ERROR: block 0 is a meta page +SELECT * FROM bt_page_stats('test1_a_idx', 1); +-[ RECORD 1 ]-+----- +blkno | 1 +type | l +live_items | 1 +dead_items | 0 +avg_item_size | 16 +page_size | 8192 +free_size | 8128 +btpo_prev | 0 +btpo_next | 0 +btpo_level | 0 +btpo_flags | 3 + +SELECT * FROM bt_page_stats('test1_a_idx', 2); +ERROR: block number out of range +SELECT * FROM bt_page_items('test1_a_idx', -1); +ERROR: invalid block number +SELECT * FROM bt_page_items('test1_a_idx', 0); +ERROR: block 0 is a meta page +SELECT * FROM bt_page_items('test1_a_idx', 1); +-[ RECORD 1 ]----------------------- +itemoffset | 1 +ctid | (0,1) +itemlen | 16 +nulls | f +vars | f +data | 01 00 00 00 00 00 00 01 +dead | f +htid | (0,1) +tids | + +SELECT * FROM bt_page_items('test1_a_idx', 2); +ERROR: block number out of range +SELECT * FROM bt_page_items(get_raw_page('test1_a_idx', -1)); +ERROR: invalid block number +SELECT * FROM bt_page_items(get_raw_page('test1_a_idx', 0)); +ERROR: block is a meta page +SELECT * FROM bt_page_items(get_raw_page('test1_a_idx', 1)); +-[ RECORD 1 ]----------------------- +itemoffset | 1 +ctid | (0,1) +itemlen | 16 +nulls | f +vars | f +data | 01 00 00 00 00 00 00 01 +dead | f +htid | (0,1) +tids | + +SELECT * FROM bt_page_items(get_raw_page('test1_a_idx', 2)); +ERROR: block number 2 is out of range for relation "test1_a_idx" +-- Failure when using a non-btree index. +CREATE INDEX test1_a_hash ON test1 USING hash(a); +SELECT bt_metap('test1_a_hash'); +ERROR: "test1_a_hash" is not a btree index +SELECT bt_page_stats('test1_a_hash', 0); +ERROR: "test1_a_hash" is not a btree index +SELECT bt_page_items('test1_a_hash', 0); +ERROR: "test1_a_hash" is not a btree index +SELECT bt_page_items(get_raw_page('test1_a_hash', 0)); +ERROR: block is a meta page +CREATE INDEX test1_b_gist ON test1 USING gist(b); +-- Special area of GiST is the same as btree, this complains about inconsistent +-- leaf data on the page. +SELECT bt_page_items(get_raw_page('test1_b_gist', 0)); +ERROR: block is not a valid btree leaf page +-- Several failure modes. +-- Suppress the DETAIL message, to allow the tests to work across various +-- page sizes and architectures. +\set VERBOSITY terse +-- invalid page size +SELECT bt_page_items('aaa'::bytea); +ERROR: invalid page size +-- invalid special area size +CREATE INDEX test1_a_brin ON test1 USING brin(a); +SELECT bt_page_items(get_raw_page('test1', 0)); +ERROR: input page is not a valid btree page +SELECT bt_page_items(get_raw_page('test1_a_brin', 0)); +ERROR: input page is not a valid btree page +\set VERBOSITY default +-- Tests with all-zero pages. +SHOW block_size \gset +SELECT bt_page_items(decode(repeat('00', :block_size), 'hex')); +-[ RECORD 1 ]-+- +bt_page_items | + +DROP TABLE test1; diff --git a/contrib/pageinspect/expected/checksum.out b/contrib/pageinspect/expected/checksum.out new file mode 100644 index 0000000..a85388e --- /dev/null +++ b/contrib/pageinspect/expected/checksum.out @@ -0,0 +1,40 @@ +-- +-- Verify correct calculation of checksums +-- +-- Postgres' checksum algorithm produces different answers on little-endian +-- and big-endian machines. The results of this test also vary depending +-- on the configured block size. This test has several different expected +-- results files to handle the following possibilities: +-- +-- BLCKSZ end file +-- 8K LE checksum.out +-- 8K BE checksum_1.out +-- +-- In future we might provide additional expected-results files for other +-- block sizes, but there seems little point as long as so many other +-- test scripts also show false failures for non-default block sizes. +-- +-- This is to label the results files with blocksize: +SHOW block_size; + block_size +------------ + 8192 +(1 row) + +SHOW block_size \gset +-- Apply page_checksum() to some different data patterns and block numbers +SELECT blkno, + page_checksum(decode(repeat('01', :block_size), 'hex'), blkno) AS checksum_01, + page_checksum(decode(repeat('04', :block_size), 'hex'), blkno) AS checksum_04, + page_checksum(decode(repeat('ff', :block_size), 'hex'), blkno) AS checksum_ff, + page_checksum(decode(repeat('abcd', :block_size / 2), 'hex'), blkno) AS checksum_abcd, + page_checksum(decode(repeat('e6d6', :block_size / 2), 'hex'), blkno) AS checksum_e6d6, + page_checksum(decode(repeat('4a5e', :block_size / 2), 'hex'), blkno) AS checksum_4a5e + FROM generate_series(0, 100, 50) AS a (blkno); + blkno | checksum_01 | checksum_04 | checksum_ff | checksum_abcd | checksum_e6d6 | checksum_4a5e +-------+-------------+-------------+-------------+---------------+---------------+--------------- + 0 | 1175 | 28338 | 3612 | -30781 | -16269 | -27377 + 50 | 1225 | 28352 | 3598 | -30795 | -16251 | -27391 + 100 | 1139 | 28438 | 3648 | -30881 | -16305 | -27349 +(3 rows) + diff --git a/contrib/pageinspect/expected/checksum_1.out b/contrib/pageinspect/expected/checksum_1.out new file mode 100644 index 0000000..6fb1b1b --- /dev/null +++ b/contrib/pageinspect/expected/checksum_1.out @@ -0,0 +1,40 @@ +-- +-- Verify correct calculation of checksums +-- +-- Postgres' checksum algorithm produces different answers on little-endian +-- and big-endian machines. The results of this test also vary depending +-- on the configured block size. This test has several different expected +-- results files to handle the following possibilities: +-- +-- BLCKSZ end file +-- 8K LE checksum.out +-- 8K BE checksum_1.out +-- +-- In future we might provide additional expected-results files for other +-- block sizes, but there seems little point as long as so many other +-- test scripts also show false failures for non-default block sizes. +-- +-- This is to label the results files with blocksize: +SHOW block_size; + block_size +------------ + 8192 +(1 row) + +SHOW block_size \gset +-- Apply page_checksum() to some different data patterns and block numbers +SELECT blkno, + page_checksum(decode(repeat('01', :block_size), 'hex'), blkno) AS checksum_01, + page_checksum(decode(repeat('04', :block_size), 'hex'), blkno) AS checksum_04, + page_checksum(decode(repeat('ff', :block_size), 'hex'), blkno) AS checksum_ff, + page_checksum(decode(repeat('abcd', :block_size / 2), 'hex'), blkno) AS checksum_abcd, + page_checksum(decode(repeat('e6d6', :block_size / 2), 'hex'), blkno) AS checksum_e6d6, + page_checksum(decode(repeat('4a5e', :block_size / 2), 'hex'), blkno) AS checksum_4a5e + FROM generate_series(0, 100, 50) AS a (blkno); + blkno | checksum_01 | checksum_04 | checksum_ff | checksum_abcd | checksum_e6d6 | checksum_4a5e +-------+-------------+-------------+-------------+---------------+---------------+--------------- + 0 | -16327 | 8766 | -2722 | 13757 | -11485 | -31426 + 50 | -16281 | 8780 | -2708 | 13771 | -11503 | -31440 + 100 | -16235 | 8866 | -2758 | 13721 | -11577 | -31518 +(3 rows) + diff --git a/contrib/pageinspect/expected/gin.out b/contrib/pageinspect/expected/gin.out new file mode 100644 index 0000000..ff1da6a --- /dev/null +++ b/contrib/pageinspect/expected/gin.out @@ -0,0 +1,71 @@ +CREATE TABLE test1 (x int, y int[]); +INSERT INTO test1 VALUES (1, ARRAY[11, 111]); +CREATE INDEX test1_y_idx ON test1 USING gin (y) WITH (fastupdate = off); +\x +SELECT * FROM gin_metapage_info(get_raw_page('test1_y_idx', 0)); +-[ RECORD 1 ]----+----------- +pending_head | 4294967295 +pending_tail | 4294967295 +tail_free_size | 0 +n_pending_pages | 0 +n_pending_tuples | 0 +n_total_pages | 2 +n_entry_pages | 1 +n_data_pages | 0 +n_entries | 2 +version | 2 + +SELECT * FROM gin_metapage_info(get_raw_page('test1_y_idx', 1)); +ERROR: input page is not a GIN metapage +DETAIL: Flags 0002, expected 0008 +SELECT * FROM gin_page_opaque_info(get_raw_page('test1_y_idx', 1)); +-[ RECORD 1 ]--------- +rightlink | 4294967295 +maxoff | 0 +flags | {leaf} + +SELECT * FROM gin_leafpage_items(get_raw_page('test1_y_idx', 1)); +ERROR: input page is not a compressed GIN data leaf page +DETAIL: Flags 0002, expected 0083 +INSERT INTO test1 SELECT x, ARRAY[1,10] FROM generate_series(2,10000) x; +SELECT COUNT(*) > 0 +FROM gin_leafpage_items(get_raw_page('test1_y_idx', + (pg_relation_size('test1_y_idx') / + current_setting('block_size')::bigint)::int - 1)); +-[ RECORD 1 ] +?column? | t + +-- Failure with various modes. +-- Suppress the DETAIL message, to allow the tests to work across various +-- page sizes and architectures. +\set VERBOSITY terse +-- invalid page size +SELECT gin_leafpage_items('aaa'::bytea); +ERROR: invalid page size +SELECT gin_metapage_info('bbb'::bytea); +ERROR: invalid page size +SELECT gin_page_opaque_info('ccc'::bytea); +ERROR: invalid page size +-- invalid special area size +SELECT * FROM gin_metapage_info(get_raw_page('test1', 0)); +ERROR: input page is not a valid GIN metapage +SELECT * FROM gin_page_opaque_info(get_raw_page('test1', 0)); +ERROR: input page is not a valid GIN data leaf page +SELECT * FROM gin_leafpage_items(get_raw_page('test1', 0)); +ERROR: input page is not a valid GIN data leaf page +\set VERBOSITY default +-- Tests with all-zero pages. +SHOW block_size \gset +SELECT gin_leafpage_items(decode(repeat('00', :block_size), 'hex')); +-[ RECORD 1 ]------+- +gin_leafpage_items | + +SELECT gin_metapage_info(decode(repeat('00', :block_size), 'hex')); +-[ RECORD 1 ]-----+- +gin_metapage_info | + +SELECT gin_page_opaque_info(decode(repeat('00', :block_size), 'hex')); +-[ RECORD 1 ]--------+- +gin_page_opaque_info | + +DROP TABLE test1; diff --git a/contrib/pageinspect/expected/gist.out b/contrib/pageinspect/expected/gist.out new file mode 100644 index 0000000..469fc5e --- /dev/null +++ b/contrib/pageinspect/expected/gist.out @@ -0,0 +1,110 @@ +-- The gist_page_opaque_info() function prints the page's LSN. Normally, +-- that's constant 1 (GistBuildLSN) on every page of a freshly built GiST +-- index. But with wal_level=minimal, the whole relation is dumped to WAL at +-- the end of the transaction if it's smaller than wal_skip_threshold, which +-- updates the LSNs. Wrap the tests on gist_page_opaque_info() in the +-- same transaction with the CREATE INDEX so that we see the LSNs before +-- they are possibly overwritten at end of transaction. +BEGIN; +-- Create a test table and GiST index. +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); +-- Page 0 is the root, the rest are leaf pages +SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 0)); + lsn | nsn | rightlink | flags +-----+-----+------------+------- + 0/1 | 0/0 | 4294967295 | {} +(1 row) + +SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 1)); + lsn | nsn | rightlink | flags +-----+-----+------------+-------- + 0/1 | 0/0 | 4294967295 | {leaf} +(1 row) + +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) + +COMMIT; +SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 0), 'test_gist_idx'); + itemoffset | ctid | itemlen | dead | keys +------------+-----------+---------+------+------------------- + 1 | (1,65535) | 40 | f | (p)=((166,166)) + 2 | (2,65535) | 40 | f | (p)=((332,332)) + 3 | (3,65535) | 40 | f | (p)=((498,498)) + 4 | (4,65535) | 40 | f | (p)=((664,664)) + 5 | (5,65535) | 40 | f | (p)=((830,830)) + 6 | (6,65535) | 40 | f | (p)=((996,996)) + 7 | (7,65535) | 40 | f | (p)=((1000,1000)) +(7 rows) + +SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 1), 'test_gist_idx') LIMIT 5; + itemoffset | ctid | itemlen | dead | keys +------------+-------+---------+------+------------- + 1 | (0,1) | 40 | f | (p)=((1,1)) + 2 | (0,2) | 40 | f | (p)=((2,2)) + 3 | (0,3) | 40 | f | (p)=((3,3)) + 4 | (0,4) | 40 | f | (p)=((4,4)) + 5 | (0,5) | 40 | f | (p)=((5,5)) +(5 rows) + +-- gist_page_items_bytea prints the raw key data as a bytea. The output of that is +-- platform-dependent (endianess), so omit the actual key data from the output. +SELECT itemoffset, ctid, itemlen FROM gist_page_items_bytea(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) + +-- Failure with non-GiST index. +CREATE INDEX test_gist_btree on test_gist(t); +SELECT gist_page_items(get_raw_page('test_gist_btree', 0), 'test_gist_btree'); +ERROR: "test_gist_btree" is not a GiST index +-- Failure with various modes. +-- Suppress the DETAIL message, to allow the tests to work across various +-- page sizes and architectures. +\set VERBOSITY terse +-- invalid page size +SELECT gist_page_items_bytea('aaa'::bytea); +ERROR: invalid page size +SELECT gist_page_items('aaa'::bytea, 'test_gist_idx'::regclass); +ERROR: invalid page size +SELECT gist_page_opaque_info('aaa'::bytea); +ERROR: invalid page size +-- invalid special area size +SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist', 0)); +ERROR: input page is not a valid GiST page +SELECT gist_page_items_bytea(get_raw_page('test_gist', 0)); +ERROR: input page is not a valid GiST page +SELECT gist_page_items_bytea(get_raw_page('test_gist_btree', 0)); +ERROR: input page is not a valid GiST page +\set VERBOSITY default +-- Tests with all-zero pages. +SHOW block_size \gset +SELECT gist_page_items_bytea(decode(repeat('00', :block_size), 'hex')); + gist_page_items_bytea +----------------------- +(0 rows) + +SELECT gist_page_items(decode(repeat('00', :block_size), 'hex'), 'test_gist_idx'::regclass); + gist_page_items +----------------- +(0 rows) + +SELECT gist_page_opaque_info(decode(repeat('00', :block_size), 'hex')); + gist_page_opaque_info +----------------------- + +(1 row) + +DROP TABLE test_gist; diff --git a/contrib/pageinspect/expected/hash.out b/contrib/pageinspect/expected/hash.out new file mode 100644 index 0000000..5d6a518 --- /dev/null +++ b/contrib/pageinspect/expected/hash.out @@ -0,0 +1,205 @@ +CREATE TABLE test_hash (a int, b text); +INSERT INTO test_hash VALUES (1, 'one'); +CREATE INDEX test_hash_a_idx ON test_hash USING hash (a); +\x +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 0)); +-[ RECORD 1 ]--+--------- +hash_page_type | metapage + +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 1)); +-[ RECORD 1 ]--+------- +hash_page_type | bucket + +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 2)); +-[ RECORD 1 ]--+------- +hash_page_type | bucket + +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 3)); +-[ RECORD 1 ]--+------- +hash_page_type | bucket + +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 4)); +-[ RECORD 1 ]--+------- +hash_page_type | bucket + +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 5)); +-[ RECORD 1 ]--+------- +hash_page_type | bitmap + +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 6)); +ERROR: block number 6 is out of range for relation "test_hash_a_idx" +SELECT * FROM hash_bitmap_info('test_hash_a_idx', -1); +ERROR: invalid block number +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 0); +ERROR: invalid overflow block number 0 +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 1); +ERROR: invalid overflow block number 1 +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 2); +ERROR: invalid overflow block number 2 +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 3); +ERROR: invalid overflow block number 3 +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 4); +ERROR: invalid overflow block number 4 +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 5); +ERROR: invalid overflow block number 5 +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 6); +ERROR: block number 6 is out of range for relation "test_hash_a_idx" +SELECT magic, version, ntuples, bsize, bmsize, bmshift, maxbucket, highmask, +lowmask, ovflpoint, firstfree, nmaps, procid, spares, mapp FROM +hash_metapage_info(get_raw_page('test_hash_a_idx', 0)); +-[ RECORD 1 ]-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- +magic | 105121344 +version | 4 +ntuples | 1 +bsize | 8152 +bmsize | 4096 +bmshift | 15 +maxbucket | 3 +highmask | 7 +lowmask | 3 +ovflpoint | 2 +firstfree | 0 +nmaps | 1 +procid | 450 +spares | {0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0} +mapp | {5,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0} + +SELECT magic, version, ntuples, bsize, bmsize, bmshift, maxbucket, highmask, +lowmask, ovflpoint, firstfree, nmaps, procid, spares, mapp FROM +hash_metapage_info(get_raw_page('test_hash_a_idx', 1)); +ERROR: page is not a hash meta page +SELECT magic, version, ntuples, bsize, bmsize, bmshift, maxbucket, highmask, +lowmask, ovflpoint, firstfree, nmaps, procid, spares, mapp FROM +hash_metapage_info(get_raw_page('test_hash_a_idx', 2)); +ERROR: page is not a hash meta page +SELECT magic, version, ntuples, bsize, bmsize, bmshift, maxbucket, highmask, +lowmask, ovflpoint, firstfree, nmaps, procid, spares, mapp FROM +hash_metapage_info(get_raw_page('test_hash_a_idx', 3)); +ERROR: page is not a hash meta page +SELECT magic, version, ntuples, bsize, bmsize, bmshift, maxbucket, highmask, +lowmask, ovflpoint, firstfree, nmaps, procid, spares, mapp FROM +hash_metapage_info(get_raw_page('test_hash_a_idx', 4)); +ERROR: page is not a hash meta page +SELECT magic, version, ntuples, bsize, bmsize, bmshift, maxbucket, highmask, +lowmask, ovflpoint, firstfree, nmaps, procid, spares, mapp FROM +hash_metapage_info(get_raw_page('test_hash_a_idx', 5)); +ERROR: page is not a hash meta page +SELECT live_items, dead_items, page_size, hasho_prevblkno, hasho_nextblkno, +hasho_bucket, hasho_flag, hasho_page_id FROM +hash_page_stats(get_raw_page('test_hash_a_idx', 0)); +ERROR: page is not a hash bucket or overflow page +SELECT live_items, dead_items, page_size, hasho_prevblkno, hasho_nextblkno, +hasho_bucket, hasho_flag, hasho_page_id FROM +hash_page_stats(get_raw_page('test_hash_a_idx', 1)); +-[ RECORD 1 ]---+----------- +live_items | 0 +dead_items | 0 +page_size | 8192 +hasho_prevblkno | 3 +hasho_nextblkno | 4294967295 +hasho_bucket | 0 +hasho_flag | 2 +hasho_page_id | 65408 + +SELECT live_items, dead_items, page_size, hasho_prevblkno, hasho_nextblkno, +hasho_bucket, hasho_flag, hasho_page_id FROM +hash_page_stats(get_raw_page('test_hash_a_idx', 2)); +-[ RECORD 1 ]---+----------- +live_items | 0 +dead_items | 0 +page_size | 8192 +hasho_prevblkno | 3 +hasho_nextblkno | 4294967295 +hasho_bucket | 1 +hasho_flag | 2 +hasho_page_id | 65408 + +SELECT live_items, dead_items, page_size, hasho_prevblkno, hasho_nextblkno, +hasho_bucket, hasho_flag, hasho_page_id FROM +hash_page_stats(get_raw_page('test_hash_a_idx', 3)); +-[ RECORD 1 ]---+----------- +live_items | 1 +dead_items | 0 +page_size | 8192 +hasho_prevblkno | 3 +hasho_nextblkno | 4294967295 +hasho_bucket | 2 +hasho_flag | 2 +hasho_page_id | 65408 + +SELECT live_items, dead_items, page_size, hasho_prevblkno, hasho_nextblkno, +hasho_bucket, hasho_flag, hasho_page_id FROM +hash_page_stats(get_raw_page('test_hash_a_idx', 4)); +-[ RECORD 1 ]---+----------- +live_items | 0 +dead_items | 0 +page_size | 8192 +hasho_prevblkno | 3 +hasho_nextblkno | 4294967295 +hasho_bucket | 3 +hasho_flag | 2 +hasho_page_id | 65408 + +SELECT live_items, dead_items, page_size, hasho_prevblkno, hasho_nextblkno, +hasho_bucket, hasho_flag, hasho_page_id FROM +hash_page_stats(get_raw_page('test_hash_a_idx', 5)); +ERROR: page is not a hash bucket or overflow page +SELECT * FROM hash_page_items(get_raw_page('test_hash_a_idx', 0)); +ERROR: page is not a hash bucket or overflow page +SELECT * FROM hash_page_items(get_raw_page('test_hash_a_idx', 1)); +(0 rows) + +SELECT * FROM hash_page_items(get_raw_page('test_hash_a_idx', 2)); +(0 rows) + +SELECT * FROM hash_page_items(get_raw_page('test_hash_a_idx', 3)); +-[ RECORD 1 ]---------- +itemoffset | 1 +ctid | (0,1) +data | 2389907270 + +SELECT * FROM hash_page_items(get_raw_page('test_hash_a_idx', 4)); +(0 rows) + +SELECT * FROM hash_page_items(get_raw_page('test_hash_a_idx', 5)); +ERROR: page is not a hash bucket or overflow page +-- Failure with non-hash index +CREATE INDEX test_hash_a_btree ON test_hash USING btree (a); +SELECT hash_bitmap_info('test_hash_a_btree', 0); +ERROR: "test_hash_a_btree" is not a hash index +-- Failure with various modes. +-- Suppress the DETAIL message, to allow the tests to work across various +-- page sizes and architectures. +\set VERBOSITY terse +-- invalid page size +SELECT hash_metapage_info('aaa'::bytea); +ERROR: invalid page size +SELECT hash_page_items('bbb'::bytea); +ERROR: invalid page size +SELECT hash_page_stats('ccc'::bytea); +ERROR: invalid page size +SELECT hash_page_type('ddd'::bytea); +ERROR: invalid page size +-- invalid special area size +SELECT hash_metapage_info(get_raw_page('test_hash', 0)); +ERROR: input page is not a valid hash page +SELECT hash_page_items(get_raw_page('test_hash', 0)); +ERROR: input page is not a valid hash page +SELECT hash_page_stats(get_raw_page('test_hash', 0)); +ERROR: input page is not a valid hash page +SELECT hash_page_type(get_raw_page('test_hash', 0)); +ERROR: input page is not a valid hash page +\set VERBOSITY default +-- Tests with all-zero pages. +SHOW block_size \gset +SELECT hash_metapage_info(decode(repeat('00', :block_size), 'hex')); +ERROR: page is not a hash meta page +SELECT hash_page_items(decode(repeat('00', :block_size), 'hex')); +ERROR: page is not a hash bucket or overflow page +SELECT hash_page_stats(decode(repeat('00', :block_size), 'hex')); +ERROR: page is not a hash bucket or overflow page +SELECT hash_page_type(decode(repeat('00', :block_size), 'hex')); +-[ RECORD 1 ]--+------- +hash_page_type | unused + +DROP TABLE test_hash; diff --git a/contrib/pageinspect/expected/oldextversions.out b/contrib/pageinspect/expected/oldextversions.out new file mode 100644 index 0000000..04dc7f8 --- /dev/null +++ b/contrib/pageinspect/expected/oldextversions.out @@ -0,0 +1,40 @@ +-- test old extension version entry points +DROP EXTENSION pageinspect; +CREATE EXTENSION pageinspect VERSION '1.8'; +CREATE TABLE test1 (a int8, b text); +INSERT INTO test1 VALUES (72057594037927937, 'text'); +CREATE INDEX test1_a_idx ON test1 USING btree (a); +-- from page.sql +SELECT octet_length(get_raw_page('test1', 0)) AS main_0; + main_0 +-------- + 8192 +(1 row) + +SELECT octet_length(get_raw_page('test1', 'main', 0)) AS main_0; + main_0 +-------- + 8192 +(1 row) + +SELECT page_checksum(get_raw_page('test1', 0), 0) IS NOT NULL AS silly_checksum_test; + silly_checksum_test +--------------------- + t +(1 row) + +-- from btree.sql +SELECT * FROM bt_page_stats('test1_a_idx', 1); + blkno | type | live_items | dead_items | avg_item_size | page_size | free_size | btpo_prev | btpo_next | btpo | btpo_flags +-------+------+------------+------------+---------------+-----------+-----------+-----------+-----------+------+------------ + 1 | l | 1 | 0 | 16 | 8192 | 8128 | 0 | 0 | 0 | 3 +(1 row) + +SELECT * FROM bt_page_items('test1_a_idx', 1); + itemoffset | ctid | itemlen | nulls | vars | data | dead | htid | tids +------------+-------+---------+-------+------+-------------------------+------+-------+------ + 1 | (0,1) | 16 | f | f | 01 00 00 00 00 00 00 01 | f | (0,1) | +(1 row) + +DROP TABLE test1; +DROP EXTENSION pageinspect; diff --git a/contrib/pageinspect/expected/page.out b/contrib/pageinspect/expected/page.out new file mode 100644 index 0000000..8134eda --- /dev/null +++ b/contrib/pageinspect/expected/page.out @@ -0,0 +1,238 @@ +CREATE EXTENSION pageinspect; +CREATE TABLE test1 (a int, b int); +INSERT INTO test1 VALUES (16777217, 131584); +VACUUM (DISABLE_PAGE_SKIPPING) test1; -- set up FSM +-- The page contents can vary, so just test that it can be read +-- successfully, but don't keep the output. +SELECT octet_length(get_raw_page('test1', 'main', 0)) AS main_0; + main_0 +-------- + 8192 +(1 row) + +SELECT octet_length(get_raw_page('test1', 'main', 1)) AS main_1; +ERROR: block number 1 is out of range for relation "test1" +SELECT octet_length(get_raw_page('test1', 'fsm', 0)) AS fsm_0; + fsm_0 +------- + 8192 +(1 row) + +SELECT octet_length(get_raw_page('test1', 'fsm', 1)) AS fsm_1; + fsm_1 +------- + 8192 +(1 row) + +SELECT octet_length(get_raw_page('test1', 'vm', 0)) AS vm_0; + vm_0 +------ + 8192 +(1 row) + +SELECT octet_length(get_raw_page('test1', 'vm', 1)) AS vm_1; +ERROR: block number 1 is out of range for relation "test1" +SELECT octet_length(get_raw_page('test1', 'main', -1)); +ERROR: invalid block number +SELECT octet_length(get_raw_page('xxx', 'main', 0)); +ERROR: relation "xxx" does not exist +SELECT octet_length(get_raw_page('test1', 'xxx', 0)); +ERROR: invalid fork name +HINT: Valid fork names are "main", "fsm", "vm", and "init". +SELECT get_raw_page('test1', 0) = get_raw_page('test1', 'main', 0); + ?column? +---------- + t +(1 row) + +SELECT pagesize, version FROM page_header(get_raw_page('test1', 0)); + pagesize | version +----------+--------- + 8192 | 4 +(1 row) + +SELECT page_checksum(get_raw_page('test1', 0), 0) IS NOT NULL AS silly_checksum_test; + silly_checksum_test +--------------------- + t +(1 row) + +SELECT page_checksum(get_raw_page('test1', 0), -1); +ERROR: invalid block number +SELECT tuple_data_split('test1'::regclass, t_data, t_infomask, t_infomask2, t_bits) + FROM heap_page_items(get_raw_page('test1', 0)); + tuple_data_split +------------------------------- + {"\\x01000001","\\x00020200"} +(1 row) + +SELECT * FROM fsm_page_contents(get_raw_page('test1', 'fsm', 0)); + fsm_page_contents +------------------- + 0: 254 + + 1: 254 + + 3: 254 + + 7: 254 + + 15: 254 + + 31: 254 + + 63: 254 + + 127: 254 + + 255: 254 + + 511: 254 + + 1023: 254 + + 2047: 254 + + 4095: 254 + + fp_next_slot: 0 + + +(1 row) + +-- If we freeze the only tuple on test1, the infomask should +-- always be the same in all test runs. +VACUUM (FREEZE, DISABLE_PAGE_SKIPPING) test1; +SELECT t_infomask, t_infomask2, raw_flags, combined_flags +FROM heap_page_items(get_raw_page('test1', 0)), + LATERAL heap_tuple_infomask_flags(t_infomask, t_infomask2); + t_infomask | t_infomask2 | raw_flags | combined_flags +------------+-------------+-----------------------------------------------------------+-------------------- + 2816 | 2 | {HEAP_XMIN_COMMITTED,HEAP_XMIN_INVALID,HEAP_XMAX_INVALID} | {HEAP_XMIN_FROZEN} +(1 row) + +-- tests for decoding of combined flags +-- HEAP_XMAX_SHR_LOCK = (HEAP_XMAX_EXCL_LOCK | HEAP_XMAX_KEYSHR_LOCK) +SELECT * FROM heap_tuple_infomask_flags(x'0050'::int, 0); + raw_flags | combined_flags +---------------------------------------------+---------------------- + {HEAP_XMAX_KEYSHR_LOCK,HEAP_XMAX_EXCL_LOCK} | {HEAP_XMAX_SHR_LOCK} +(1 row) + +-- HEAP_XMIN_FROZEN = (HEAP_XMIN_COMMITTED | HEAP_XMIN_INVALID) +SELECT * FROM heap_tuple_infomask_flags(x'0300'::int, 0); + raw_flags | combined_flags +-----------------------------------------+-------------------- + {HEAP_XMIN_COMMITTED,HEAP_XMIN_INVALID} | {HEAP_XMIN_FROZEN} +(1 row) + +-- HEAP_MOVED = (HEAP_MOVED_IN | HEAP_MOVED_OFF) +SELECT * FROM heap_tuple_infomask_flags(x'C000'::int, 0); + raw_flags | combined_flags +--------------------------------+---------------- + {HEAP_MOVED_OFF,HEAP_MOVED_IN} | {HEAP_MOVED} +(1 row) + +SELECT * FROM heap_tuple_infomask_flags(x'C000'::int, 0); + raw_flags | combined_flags +--------------------------------+---------------- + {HEAP_MOVED_OFF,HEAP_MOVED_IN} | {HEAP_MOVED} +(1 row) + +-- test all flags of t_infomask and t_infomask2 +SELECT unnest(raw_flags) + FROM heap_tuple_infomask_flags(x'FFFF'::int, x'FFFF'::int) ORDER BY 1; + unnest +----------------------- + HEAP_COMBOCID + HEAP_HASEXTERNAL + HEAP_HASNULL + HEAP_HASOID_OLD + HEAP_HASVARWIDTH + HEAP_HOT_UPDATED + HEAP_KEYS_UPDATED + HEAP_MOVED_IN + HEAP_MOVED_OFF + HEAP_ONLY_TUPLE + HEAP_UPDATED + HEAP_XMAX_COMMITTED + HEAP_XMAX_EXCL_LOCK + HEAP_XMAX_INVALID + HEAP_XMAX_IS_MULTI + HEAP_XMAX_KEYSHR_LOCK + HEAP_XMAX_LOCK_ONLY + HEAP_XMIN_COMMITTED + HEAP_XMIN_INVALID +(19 rows) + +SELECT unnest(combined_flags) + FROM heap_tuple_infomask_flags(x'FFFF'::int, x'FFFF'::int) ORDER BY 1; + unnest +-------------------- + HEAP_MOVED + HEAP_XMAX_SHR_LOCK + HEAP_XMIN_FROZEN +(3 rows) + +-- no flags at all +SELECT * FROM heap_tuple_infomask_flags(0, 0); + raw_flags | combined_flags +-----------+---------------- + {} | {} +(1 row) + +-- no combined flags +SELECT * FROM heap_tuple_infomask_flags(x'0010'::int, 0); + raw_flags | combined_flags +-------------------------+---------------- + {HEAP_XMAX_KEYSHR_LOCK} | {} +(1 row) + +DROP TABLE test1; +-- check that using any of these functions with a partitioned table or index +-- would fail +create table test_partitioned (a int) partition by range (a); +create index test_partitioned_index on test_partitioned (a); +select get_raw_page('test_partitioned', 0); -- error about partitioned table +ERROR: cannot get raw page from partitioned table "test_partitioned" +select get_raw_page('test_partitioned_index', 0); -- error about partitioned index +ERROR: cannot get raw page from partitioned index "test_partitioned_index" +-- a regular table which is a member of a partition set should work though +create table test_part1 partition of test_partitioned for values from ( 1 ) to (100); +select get_raw_page('test_part1', 0); -- get farther and error about empty table +ERROR: block number 0 is out of range for relation "test_part1" +drop table test_partitioned; +-- check null bitmap alignment for table whose number of attributes is multiple of 8 +create table test8 (f1 int, f2 int, f3 int, f4 int, f5 int, f6 int, f7 int, f8 int); +insert into test8(f1, f8) values (x'7f00007f'::int, 0); +select t_bits, t_data from heap_page_items(get_raw_page('test8', 0)); + t_bits | t_data +----------+-------------------- + 10000001 | \x7f00007f00000000 +(1 row) + +select tuple_data_split('test8'::regclass, t_data, t_infomask, t_infomask2, t_bits) + from heap_page_items(get_raw_page('test8', 0)); + tuple_data_split +------------------------------------------------------------- + {"\\x7f00007f",NULL,NULL,NULL,NULL,NULL,NULL,"\\x00000000"} +(1 row) + +drop table test8; +-- Failure with incorrect page size +-- Suppress the DETAIL message, to allow the tests to work across various +-- page sizes. +\set VERBOSITY terse +SELECT fsm_page_contents('aaa'::bytea); +ERROR: invalid page size +SELECT page_checksum('bbb'::bytea, 0); +ERROR: invalid page size +SELECT page_header('ccc'::bytea); +ERROR: invalid page size +\set VERBOSITY default +-- Tests with all-zero pages. +SHOW block_size \gset +SELECT fsm_page_contents(decode(repeat('00', :block_size), 'hex')); + fsm_page_contents +------------------- + +(1 row) + +SELECT page_header(decode(repeat('00', :block_size), 'hex')); + page_header +----------------------- + (0/0,0,0,0,0,0,0,0,0) +(1 row) + +SELECT page_checksum(decode(repeat('00', :block_size), 'hex'), 1); + page_checksum +--------------- + +(1 row) + diff --git a/contrib/pageinspect/fsmfuncs.c b/contrib/pageinspect/fsmfuncs.c new file mode 100644 index 0000000..7192750 --- /dev/null +++ b/contrib/pageinspect/fsmfuncs.c @@ -0,0 +1,65 @@ +/*------------------------------------------------------------------------- + * + * fsmfuncs.c + * Functions to investigate FSM pages + * + * These functions are restricted to superusers for the fear of introducing + * security holes if the input checking isn't as water-tight as it should. + * You'd need to be superuser to obtain a raw page image anyway, so + * there's hardly any use case for using these without superuser-rights + * anyway. + * + * Copyright (c) 2007-2021, PostgreSQL Global Development Group + * + * IDENTIFICATION + * contrib/pageinspect/fsmfuncs.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "funcapi.h" +#include "lib/stringinfo.h" +#include "miscadmin.h" +#include "pageinspect.h" +#include "storage/fsm_internals.h" +#include "utils/builtins.h" + +/* + * Dumps the contents of a FSM page. + */ +PG_FUNCTION_INFO_V1(fsm_page_contents); + +Datum +fsm_page_contents(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + StringInfoData sinfo; + Page page; + FSMPage fsmpage; + int i; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + page = get_page_from_raw(raw_page); + + if (PageIsNew(page)) + PG_RETURN_NULL(); + + fsmpage = (FSMPage) PageGetContents(page); + + initStringInfo(&sinfo); + + for (i = 0; i < NodesPerPage; i++) + { + if (fsmpage->fp_nodes[i] != 0) + appendStringInfo(&sinfo, "%d: %d\n", i, fsmpage->fp_nodes[i]); + } + appendStringInfo(&sinfo, "fp_next_slot: %d\n", fsmpage->fp_next_slot); + + PG_RETURN_TEXT_P(cstring_to_text_with_len(sinfo.data, sinfo.len)); +} diff --git a/contrib/pageinspect/ginfuncs.c b/contrib/pageinspect/ginfuncs.c new file mode 100644 index 0000000..7a297f1 --- /dev/null +++ b/contrib/pageinspect/ginfuncs.c @@ -0,0 +1,293 @@ +/* + * ginfuncs.c + * Functions to investigate the content of GIN indexes + * + * Copyright (c) 2014-2021, PostgreSQL Global Development Group + * + * IDENTIFICATION + * contrib/pageinspect/ginfuncs.c + */ +#include "postgres.h" + +#include "access/gin.h" +#include "access/gin_private.h" +#include "access/htup_details.h" +#include "catalog/namespace.h" +#include "catalog/pg_type.h" +#include "funcapi.h" +#include "miscadmin.h" +#include "pageinspect.h" +#include "utils/array.h" +#include "utils/builtins.h" +#include "utils/rel.h" + +#define DatumGetItemPointer(X) ((ItemPointer) DatumGetPointer(X)) +#define ItemPointerGetDatum(X) PointerGetDatum(X) + + +PG_FUNCTION_INFO_V1(gin_metapage_info); +PG_FUNCTION_INFO_V1(gin_page_opaque_info); +PG_FUNCTION_INFO_V1(gin_leafpage_items); + + +Datum +gin_metapage_info(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + TupleDesc tupdesc; + Page page; + GinPageOpaque opaq; + GinMetaPageData *metadata; + HeapTuple resultTuple; + Datum values[10]; + bool nulls[10]; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + page = get_page_from_raw(raw_page); + + if (PageIsNew(page)) + PG_RETURN_NULL(); + + if (PageGetSpecialSize(page) != MAXALIGN(sizeof(GinPageOpaqueData))) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a valid GIN metapage"), + errdetail("Expected special size %d, got %d.", + (int) MAXALIGN(sizeof(GinPageOpaqueData)), + (int) PageGetSpecialSize(page)))); + + opaq = (GinPageOpaque) PageGetSpecialPointer(page); + if (opaq->flags != GIN_META) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a GIN metapage"), + errdetail("Flags %04X, expected %04X", + opaq->flags, GIN_META))); + + /* 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"); + + metadata = GinPageGetMeta(page); + + memset(nulls, 0, sizeof(nulls)); + + values[0] = Int64GetDatum(metadata->head); + values[1] = Int64GetDatum(metadata->tail); + values[2] = Int32GetDatum(metadata->tailFreeSize); + values[3] = Int64GetDatum(metadata->nPendingPages); + values[4] = Int64GetDatum(metadata->nPendingHeapTuples); + + /* statistics, updated by VACUUM */ + values[5] = Int64GetDatum(metadata->nTotalPages); + values[6] = Int64GetDatum(metadata->nEntryPages); + values[7] = Int64GetDatum(metadata->nDataPages); + values[8] = Int64GetDatum(metadata->nEntries); + + values[9] = Int32GetDatum(metadata->ginVersion); + + /* Build and return the result tuple. */ + resultTuple = heap_form_tuple(tupdesc, values, nulls); + + return HeapTupleGetDatum(resultTuple); +} + + +Datum +gin_page_opaque_info(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + TupleDesc tupdesc; + Page page; + GinPageOpaque opaq; + HeapTuple resultTuple; + Datum values[3]; + bool nulls[3]; + 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); + + if (PageIsNew(page)) + PG_RETURN_NULL(); + + if (PageGetSpecialSize(page) != MAXALIGN(sizeof(GinPageOpaqueData))) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a valid GIN data leaf page"), + errdetail("Expected special size %d, got %d.", + (int) MAXALIGN(sizeof(GinPageOpaqueData)), + (int) PageGetSpecialSize(page)))); + + opaq = (GinPageOpaque) 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 & GIN_DATA) + flags[nflags++] = CStringGetTextDatum("data"); + if (flagbits & GIN_LEAF) + flags[nflags++] = CStringGetTextDatum("leaf"); + if (flagbits & GIN_DELETED) + flags[nflags++] = CStringGetTextDatum("deleted"); + if (flagbits & GIN_META) + flags[nflags++] = CStringGetTextDatum("meta"); + if (flagbits & GIN_LIST) + flags[nflags++] = CStringGetTextDatum("list"); + if (flagbits & GIN_LIST_FULLROW) + flags[nflags++] = CStringGetTextDatum("list_fullrow"); + if (flagbits & GIN_INCOMPLETE_SPLIT) + flags[nflags++] = CStringGetTextDatum("incomplete_split"); + if (flagbits & GIN_COMPRESSED) + flags[nflags++] = CStringGetTextDatum("compressed"); + flagbits &= ~(GIN_DATA | GIN_LEAF | GIN_DELETED | GIN_META | GIN_LIST | + GIN_LIST_FULLROW | GIN_INCOMPLETE_SPLIT | GIN_COMPRESSED); + 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] = Int64GetDatum(opaq->rightlink); + values[1] = Int32GetDatum(opaq->maxoff); + values[2] = 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 gin_leafpage_items_state +{ + TupleDesc tupd; + GinPostingList *seg; + GinPostingList *lastseg; +} gin_leafpage_items_state; + +Datum +gin_leafpage_items(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + FuncCallContext *fctx; + gin_leafpage_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; + GinPageOpaque opaq; + + fctx = SRF_FIRSTCALL_INIT(); + mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx); + + page = get_page_from_raw(raw_page); + + if (PageIsNew(page)) + { + MemoryContextSwitchTo(mctx); + PG_RETURN_NULL(); + } + + if (PageGetSpecialSize(page) != MAXALIGN(sizeof(GinPageOpaqueData))) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a valid GIN data leaf page"), + errdetail("Expected special size %d, got %d.", + (int) MAXALIGN(sizeof(GinPageOpaqueData)), + (int) PageGetSpecialSize(page)))); + + opaq = (GinPageOpaque) PageGetSpecialPointer(page); + if (opaq->flags != (GIN_DATA | GIN_LEAF | GIN_COMPRESSED)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a compressed GIN data leaf page"), + errdetail("Flags %04X, expected %04X", + opaq->flags, + (GIN_DATA | GIN_LEAF | GIN_COMPRESSED)))); + + inter_call_data = palloc(sizeof(gin_leafpage_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->tupd = tupdesc; + + inter_call_data->seg = GinDataLeafPageGetPostingList(page); + inter_call_data->lastseg = (GinPostingList *) + (((char *) inter_call_data->seg) + + GinDataLeafPageGetPostingListSize(page)); + + fctx->user_fctx = inter_call_data; + + MemoryContextSwitchTo(mctx); + } + + fctx = SRF_PERCALL_SETUP(); + inter_call_data = fctx->user_fctx; + + if (inter_call_data->seg != inter_call_data->lastseg) + { + GinPostingList *cur = inter_call_data->seg; + HeapTuple resultTuple; + Datum result; + Datum values[3]; + bool nulls[3]; + int ndecoded, + i; + ItemPointer tids; + Datum *tids_datum; + + memset(nulls, 0, sizeof(nulls)); + + values[0] = ItemPointerGetDatum(&cur->first); + values[1] = UInt16GetDatum(cur->nbytes); + + /* build an array of decoded item pointers */ + tids = ginPostingListDecode(cur, &ndecoded); + tids_datum = (Datum *) palloc(ndecoded * sizeof(Datum)); + for (i = 0; i < ndecoded; i++) + tids_datum[i] = ItemPointerGetDatum(&tids[i]); + values[2] = PointerGetDatum(construct_array(tids_datum, + ndecoded, + TIDOID, + sizeof(ItemPointerData), + false, TYPALIGN_SHORT)); + pfree(tids_datum); + pfree(tids); + + /* Build and return the result tuple. */ + resultTuple = heap_form_tuple(inter_call_data->tupd, values, nulls); + result = HeapTupleGetDatum(resultTuple); + + inter_call_data->seg = GinNextPostingListSegment(cur); + + SRF_RETURN_NEXT(fctx, result); + } + + SRF_RETURN_DONE(fctx); +} diff --git a/contrib/pageinspect/gistfuncs.c b/contrib/pageinspect/gistfuncs.c new file mode 100644 index 0000000..d1c3c32 --- /dev/null +++ b/contrib/pageinspect/gistfuncs.c @@ -0,0 +1,337 @@ +/* + * gistfuncs.c + * Functions to investigate the content of GiST indexes + * + * Copyright (c) 2014-2021, PostgreSQL Global Development Group + * + * IDENTIFICATION + * contrib/pageinspect/gistfuncs.c + */ +#include "postgres.h" + +#include "access/gist.h" +#include "access/gist_private.h" +#include "access/htup.h" +#include "access/relation.h" +#include "catalog/namespace.h" +#include "catalog/pg_am_d.h" +#include "funcapi.h" +#include "miscadmin.h" +#include "pageinspect.h" +#include "storage/itemptr.h" +#include "utils/array.h" +#include "utils/builtins.h" +#include "utils/rel.h" +#include "utils/pg_lsn.h" +#include "utils/varlena.h" + +PG_FUNCTION_INFO_V1(gist_page_opaque_info); +PG_FUNCTION_INFO_V1(gist_page_items); +PG_FUNCTION_INFO_V1(gist_page_items_bytea); + +#define IS_GIST(r) ((r)->rd_rel->relam == GIST_AM_OID) + +#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); + + if (PageIsNew(page)) + PG_RETURN_NULL(); + + /* verify the special space has the expected size */ + if (PageGetSpecialSize(page) != MAXALIGN(sizeof(GISTPageOpaqueData))) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a valid %s page", "GiST"), + errdetail("Expected special size %d, got %d.", + (int) MAXALIGN(sizeof(GISTPageOpaqueData)), + (int) PageGetSpecialSize(page)))); + + opaq = (GISTPageOpaque) PageGetSpecialPointer(page); + if (opaq->gist_page_id != GIST_PAGE_ID) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a valid %s page", "GiST"), + errdetail("Expected %08x, got %08x.", + GIST_PAGE_ID, + opaq->gist_page_id))); + + /* 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); +} + +Datum +gist_page_items_bytea(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; + bool randomAccess; + TupleDesc tupdesc; + Tuplestorestate *tupstore; + MemoryContext oldcontext; + Page page; + GISTPageOpaque opaq; + OffsetNumber offset; + OffsetNumber maxoff = InvalidOffsetNumber; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + /* check to see if caller supports us returning a tuplestore */ + if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("set-valued function called in context that cannot accept a set"))); + if (!(rsinfo->allowedModes & SFRM_Materialize)) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("materialize mode required, but it is not allowed in this context"))); + + /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ + oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); + + if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; + tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); + rsinfo->returnMode = SFRM_Materialize; + rsinfo->setResult = tupstore; + rsinfo->setDesc = tupdesc; + + MemoryContextSwitchTo(oldcontext); + + page = get_page_from_raw(raw_page); + + if (PageIsNew(page)) + PG_RETURN_NULL(); + + /* verify the special space has the expected size */ + if (PageGetSpecialSize(page) != MAXALIGN(sizeof(GISTPageOpaqueData))) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a valid %s page", "GiST"), + errdetail("Expected special size %d, got %d.", + (int) MAXALIGN(sizeof(GISTPageOpaqueData)), + (int) PageGetSpecialSize(page)))); + + opaq = (GISTPageOpaque) PageGetSpecialPointer(page); + if (opaq->gist_page_id != GIST_PAGE_ID) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a valid %s page", "GiST"), + errdetail("Expected %08x, got %08x.", + GIST_PAGE_ID, + opaq->gist_page_id))); + + /* Avoid bogus PageGetMaxOffsetNumber() call with deleted pages */ + if (GistPageIsDeleted(page)) + elog(NOTICE, "page is deleted"); + else + maxoff = PageGetMaxOffsetNumber(page); + + for (offset = FirstOffsetNumber; + offset <= maxoff; + offset++) + { + Datum values[5]; + bool nulls[5]; + ItemId id; + IndexTuple itup; + bytea *tuple_bytea; + int tuple_len; + + id = PageGetItemId(page, offset); + + if (!ItemIdIsValid(id)) + elog(ERROR, "invalid ItemId"); + + itup = (IndexTuple) PageGetItem(page, id); + tuple_len = IndexTupleSize(itup); + + memset(nulls, 0, sizeof(nulls)); + + values[0] = DatumGetInt16(offset); + values[1] = ItemPointerGetDatum(&itup->t_tid); + values[2] = Int32GetDatum((int) IndexTupleSize(itup)); + + tuple_bytea = (bytea *) palloc(tuple_len + VARHDRSZ); + SET_VARSIZE(tuple_bytea, tuple_len + VARHDRSZ); + memcpy(VARDATA(tuple_bytea), itup, tuple_len); + values[3] = BoolGetDatum(ItemIdIsDead(id)); + values[4] = PointerGetDatum(tuple_bytea); + + tuplestore_putvalues(tupstore, tupdesc, values, nulls); + } + + return (Datum) 0; +} + +Datum +gist_page_items(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + Oid indexRelid = PG_GETARG_OID(1); + ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; + bool randomAccess; + Relation indexRel; + TupleDesc tupdesc; + Tuplestorestate *tupstore; + MemoryContext oldcontext; + Page page; + OffsetNumber offset; + OffsetNumber maxoff = InvalidOffsetNumber; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + /* check to see if caller supports us returning a tuplestore */ + if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("set-valued function called in context that cannot accept a set"))); + if (!(rsinfo->allowedModes & SFRM_Materialize)) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("materialize mode required, but it is not allowed in this context"))); + + /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ + oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); + + if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; + tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); + rsinfo->returnMode = SFRM_Materialize; + rsinfo->setResult = tupstore; + rsinfo->setDesc = tupdesc; + + MemoryContextSwitchTo(oldcontext); + + /* Open the relation */ + indexRel = index_open(indexRelid, AccessShareLock); + + if (!IS_GIST(indexRel)) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("\"%s\" is not a %s index", + RelationGetRelationName(indexRel), "GiST"))); + + page = get_page_from_raw(raw_page); + + if (PageIsNew(page)) + { + index_close(indexRel, AccessShareLock); + PG_RETURN_NULL(); + } + + /* Avoid bogus PageGetMaxOffsetNumber() call with deleted pages */ + if (GistPageIsDeleted(page)) + elog(NOTICE, "page is deleted"); + else + maxoff = PageGetMaxOffsetNumber(page); + + for (offset = FirstOffsetNumber; + offset <= maxoff; + offset++) + { + Datum values[5]; + bool nulls[5]; + ItemId id; + IndexTuple itup; + Datum itup_values[INDEX_MAX_KEYS]; + bool itup_isnull[INDEX_MAX_KEYS]; + char *key_desc; + + id = PageGetItemId(page, offset); + + if (!ItemIdIsValid(id)) + elog(ERROR, "invalid ItemId"); + + itup = (IndexTuple) PageGetItem(page, id); + + index_deform_tuple(itup, RelationGetDescr(indexRel), + itup_values, itup_isnull); + + memset(nulls, 0, sizeof(nulls)); + + values[0] = DatumGetInt16(offset); + values[1] = ItemPointerGetDatum(&itup->t_tid); + values[2] = Int32GetDatum((int) IndexTupleSize(itup)); + values[3] = BoolGetDatum(ItemIdIsDead(id)); + + key_desc = BuildIndexValueDescription(indexRel, itup_values, itup_isnull); + if (key_desc) + values[4] = CStringGetTextDatum(key_desc); + else + { + values[4] = (Datum) 0; + nulls[4] = true; + } + + tuplestore_putvalues(tupstore, tupdesc, values, nulls); + } + + relation_close(indexRel, AccessShareLock); + + return (Datum) 0; +} diff --git a/contrib/pageinspect/hashfuncs.c b/contrib/pageinspect/hashfuncs.c new file mode 100644 index 0000000..db9dd7e --- /dev/null +++ b/contrib/pageinspect/hashfuncs.c @@ -0,0 +1,586 @@ +/* + * hashfuncs.c + * Functions to investigate the content of HASH indexes + * + * Copyright (c) 2017-2021, PostgreSQL Global Development Group + * + * IDENTIFICATION + * contrib/pageinspect/hashfuncs.c + */ + +#include "postgres.h" + +#include "access/hash.h" +#include "access/htup_details.h" +#include "catalog/pg_am.h" +#include "catalog/pg_type.h" +#include "funcapi.h" +#include "miscadmin.h" +#include "pageinspect.h" +#include "utils/array.h" +#include "utils/builtins.h" +#include "utils/rel.h" + +PG_FUNCTION_INFO_V1(hash_page_type); +PG_FUNCTION_INFO_V1(hash_page_stats); +PG_FUNCTION_INFO_V1(hash_page_items); +PG_FUNCTION_INFO_V1(hash_bitmap_info); +PG_FUNCTION_INFO_V1(hash_metapage_info); + +#define IS_HASH(r) ((r)->rd_rel->relam == HASH_AM_OID) + +/* ------------------------------------------------ + * structure for single hash page statistics + * ------------------------------------------------ + */ +typedef struct HashPageStat +{ + int live_items; + int dead_items; + int page_size; + int free_size; + + /* opaque data */ + BlockNumber hasho_prevblkno; + BlockNumber hasho_nextblkno; + Bucket hasho_bucket; + uint16 hasho_flag; + uint16 hasho_page_id; +} HashPageStat; + + +/* + * Verify that the given bytea contains a HASH page, or die in the attempt. + * A pointer to a palloc'd, properly aligned copy of the page is returned. + */ +static Page +verify_hash_page(bytea *raw_page, int flags) +{ + Page page = get_page_from_raw(raw_page); + int pagetype = LH_UNUSED_PAGE; + + /* Treat new pages as unused. */ + if (!PageIsNew(page)) + { + HashPageOpaque pageopaque; + + if (PageGetSpecialSize(page) != MAXALIGN(sizeof(HashPageOpaqueData))) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a valid %s page", "hash"), + errdetail("Expected special size %d, got %d.", + (int) MAXALIGN(sizeof(HashPageOpaqueData)), + (int) PageGetSpecialSize(page)))); + + pageopaque = (HashPageOpaque) PageGetSpecialPointer(page); + if (pageopaque->hasho_page_id != HASHO_PAGE_ID) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page is not a valid %s page", "hash"), + errdetail("Expected %08x, got %08x.", + HASHO_PAGE_ID, pageopaque->hasho_page_id))); + + pagetype = pageopaque->hasho_flag & LH_PAGE_TYPE; + } + + /* Check that page type is sane. */ + if (pagetype != LH_OVERFLOW_PAGE && pagetype != LH_BUCKET_PAGE && + pagetype != LH_BITMAP_PAGE && pagetype != LH_META_PAGE && + pagetype != LH_UNUSED_PAGE) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid hash page type %08x", pagetype))); + + /* If requested, verify page type. */ + if (flags != 0 && (pagetype & flags) == 0) + { + switch (flags) + { + case LH_META_PAGE: + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("page is not a hash meta page"))); + break; + case LH_BUCKET_PAGE | LH_OVERFLOW_PAGE: + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("page is not a hash bucket or overflow page"))); + break; + case LH_OVERFLOW_PAGE: + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("page is not a hash overflow page"))); + break; + default: + elog(ERROR, + "hash page of type %08x not in mask %08x", + pagetype, flags); + break; + } + } + + /* + * If it is the metapage, also verify magic number and version. + */ + if (pagetype == LH_META_PAGE) + { + HashMetaPage metap = HashPageGetMeta(page); + + if (metap->hashm_magic != HASH_MAGIC) + ereport(ERROR, + (errcode(ERRCODE_INDEX_CORRUPTED), + errmsg("invalid magic number for metadata"), + errdetail("Expected 0x%08x, got 0x%08x.", + HASH_MAGIC, metap->hashm_magic))); + + if (metap->hashm_version != HASH_VERSION) + ereport(ERROR, + (errcode(ERRCODE_INDEX_CORRUPTED), + errmsg("invalid version for metadata"), + errdetail("Expected %d, got %d.", + HASH_VERSION, metap->hashm_version))); + } + + return page; +} + +/* ------------------------------------------------- + * GetHashPageStatistics() + * + * Collect statistics of single hash page + * ------------------------------------------------- + */ +static void +GetHashPageStatistics(Page page, HashPageStat *stat) +{ + OffsetNumber maxoff = PageGetMaxOffsetNumber(page); + HashPageOpaque opaque = (HashPageOpaque) PageGetSpecialPointer(page); + int off; + + stat->dead_items = stat->live_items = 0; + stat->page_size = PageGetPageSize(page); + + /* hash page opaque data */ + stat->hasho_prevblkno = opaque->hasho_prevblkno; + stat->hasho_nextblkno = opaque->hasho_nextblkno; + stat->hasho_bucket = opaque->hasho_bucket; + stat->hasho_flag = opaque->hasho_flag; + stat->hasho_page_id = opaque->hasho_page_id; + + /* count live and dead tuples, and free space */ + for (off = FirstOffsetNumber; off <= maxoff; off++) + { + ItemId id = PageGetItemId(page, off); + + if (!ItemIdIsDead(id)) + stat->live_items++; + else + stat->dead_items++; + } + stat->free_size = PageGetFreeSpace(page); +} + +/* --------------------------------------------------- + * hash_page_type() + * + * Usage: SELECT hash_page_type(get_raw_page('con_hash_index', 1)); + * --------------------------------------------------- + */ +Datum +hash_page_type(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + Page page; + HashPageOpaque opaque; + int pagetype; + const char *type; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + page = verify_hash_page(raw_page, 0); + + if (PageIsNew(page)) + type = "unused"; + else + { + opaque = (HashPageOpaque) PageGetSpecialPointer(page); + + /* page type (flags) */ + pagetype = opaque->hasho_flag & LH_PAGE_TYPE; + if (pagetype == LH_META_PAGE) + type = "metapage"; + else if (pagetype == LH_OVERFLOW_PAGE) + type = "overflow"; + else if (pagetype == LH_BUCKET_PAGE) + type = "bucket"; + else if (pagetype == LH_BITMAP_PAGE) + type = "bitmap"; + else + type = "unused"; + } + + PG_RETURN_TEXT_P(cstring_to_text(type)); +} + +/* --------------------------------------------------- + * hash_page_stats() + * + * Usage: SELECT * FROM hash_page_stats(get_raw_page('con_hash_index', 1)); + * --------------------------------------------------- + */ +Datum +hash_page_stats(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + Page page; + int j; + Datum values[9]; + bool nulls[9]; + HashPageStat stat; + HeapTuple tuple; + TupleDesc tupleDesc; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + page = verify_hash_page(raw_page, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE); + + /* keep compiler quiet */ + stat.hasho_prevblkno = stat.hasho_nextblkno = InvalidBlockNumber; + stat.hasho_flag = stat.hasho_page_id = stat.free_size = 0; + + GetHashPageStatistics(page, &stat); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + tupleDesc = BlessTupleDesc(tupleDesc); + + MemSet(nulls, 0, sizeof(nulls)); + + j = 0; + values[j++] = Int32GetDatum(stat.live_items); + values[j++] = Int32GetDatum(stat.dead_items); + values[j++] = Int32GetDatum(stat.page_size); + values[j++] = Int32GetDatum(stat.free_size); + values[j++] = Int64GetDatum((int64) stat.hasho_prevblkno); + values[j++] = Int64GetDatum((int64) stat.hasho_nextblkno); + values[j++] = Int64GetDatum((int64) stat.hasho_bucket); + values[j++] = Int32GetDatum((int32) stat.hasho_flag); + values[j++] = Int32GetDatum((int32) stat.hasho_page_id); + + tuple = heap_form_tuple(tupleDesc, values, nulls); + + PG_RETURN_DATUM(HeapTupleGetDatum(tuple)); +} + +/* + * cross-call data structure for SRF + */ +struct user_args +{ + Page page; + OffsetNumber offset; +}; + +/*------------------------------------------------------- + * hash_page_items() + * + * Get IndexTupleData set in a hash page + * + * Usage: SELECT * FROM hash_page_items(get_raw_page('con_hash_index', 1)); + *------------------------------------------------------- + */ +Datum +hash_page_items(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + Page page; + Datum result; + Datum values[3]; + bool nulls[3]; + uint32 hashkey; + HeapTuple tuple; + FuncCallContext *fctx; + MemoryContext mctx; + struct user_args *uargs; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + if (SRF_IS_FIRSTCALL()) + { + TupleDesc tupleDesc; + + fctx = SRF_FIRSTCALL_INIT(); + + mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx); + + page = verify_hash_page(raw_page, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE); + + uargs = palloc(sizeof(struct user_args)); + + uargs->page = page; + + uargs->offset = FirstOffsetNumber; + + fctx->max_calls = PageGetMaxOffsetNumber(uargs->page); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + tupleDesc = BlessTupleDesc(tupleDesc); + + fctx->attinmeta = TupleDescGetAttInMetadata(tupleDesc); + + fctx->user_fctx = uargs; + + MemoryContextSwitchTo(mctx); + } + + fctx = SRF_PERCALL_SETUP(); + uargs = fctx->user_fctx; + + if (fctx->call_cntr < fctx->max_calls) + { + ItemId id; + IndexTuple itup; + int j; + + id = PageGetItemId(uargs->page, uargs->offset); + + if (!ItemIdIsValid(id)) + elog(ERROR, "invalid ItemId"); + + itup = (IndexTuple) PageGetItem(uargs->page, id); + + MemSet(nulls, 0, sizeof(nulls)); + + j = 0; + values[j++] = Int32GetDatum((int32) uargs->offset); + values[j++] = PointerGetDatum(&itup->t_tid); + + hashkey = _hash_get_indextuple_hashkey(itup); + values[j] = Int64GetDatum((int64) hashkey); + + tuple = heap_form_tuple(fctx->attinmeta->tupdesc, values, nulls); + result = HeapTupleGetDatum(tuple); + + uargs->offset = uargs->offset + 1; + + SRF_RETURN_NEXT(fctx, result); + } + + SRF_RETURN_DONE(fctx); +} + +/* ------------------------------------------------ + * hash_bitmap_info() + * + * Get bitmap information for a particular overflow page + * + * Usage: SELECT * FROM hash_bitmap_info('con_hash_index'::regclass, 5); + * ------------------------------------------------ + */ +Datum +hash_bitmap_info(PG_FUNCTION_ARGS) +{ + Oid indexRelid = PG_GETARG_OID(0); + int64 ovflblkno = PG_GETARG_INT64(1); + HashMetaPage metap; + Buffer metabuf, + mapbuf; + BlockNumber bitmapblkno; + Page mappage; + bool bit = false; + TupleDesc tupleDesc; + Relation indexRel; + uint32 ovflbitno; + int32 bitmappage, + bitmapbit; + HeapTuple tuple; + int i, + j; + Datum values[3]; + bool nulls[3]; + uint32 *freep; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + indexRel = index_open(indexRelid, AccessShareLock); + + if (!IS_HASH(indexRel)) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("\"%s\" is not a %s index", + RelationGetRelationName(indexRel), "hash"))); + + if (RELATION_IS_OTHER_TEMP(indexRel)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot access temporary tables of other sessions"))); + + if (ovflblkno < 0 || ovflblkno > MaxBlockNumber) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid block number"))); + + if (ovflblkno >= RelationGetNumberOfBlocks(indexRel)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("block number %lld is out of range for relation \"%s\"", + (long long int) ovflblkno, RelationGetRelationName(indexRel)))); + + /* Read the metapage so we can determine which bitmap page to use */ + metabuf = _hash_getbuf(indexRel, HASH_METAPAGE, HASH_READ, LH_META_PAGE); + metap = HashPageGetMeta(BufferGetPage(metabuf)); + + /* + * Reject attempt to read the bit for a metapage or bitmap page; this is + * only meaningful for overflow pages. + */ + if (ovflblkno == 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid overflow block number %u", + (BlockNumber) ovflblkno))); + for (i = 0; i < metap->hashm_nmaps; i++) + if (metap->hashm_mapp[i] == ovflblkno) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid overflow block number %u", + (BlockNumber) ovflblkno))); + + /* + * Identify overflow bit number. This will error out for primary bucket + * pages, and we've already rejected the metapage and bitmap pages above. + */ + ovflbitno = _hash_ovflblkno_to_bitno(metap, (BlockNumber) ovflblkno); + + bitmappage = ovflbitno >> BMPG_SHIFT(metap); + bitmapbit = ovflbitno & BMPG_MASK(metap); + + if (bitmappage >= metap->hashm_nmaps) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid overflow block number %u", + (BlockNumber) ovflblkno))); + + bitmapblkno = metap->hashm_mapp[bitmappage]; + + _hash_relbuf(indexRel, metabuf); + + /* Check the status of bitmap bit for overflow page */ + mapbuf = _hash_getbuf(indexRel, bitmapblkno, HASH_READ, LH_BITMAP_PAGE); + mappage = BufferGetPage(mapbuf); + freep = HashPageGetBitmap(mappage); + + bit = ISSET(freep, bitmapbit) != 0; + + _hash_relbuf(indexRel, mapbuf); + index_close(indexRel, AccessShareLock); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + tupleDesc = BlessTupleDesc(tupleDesc); + + MemSet(nulls, 0, sizeof(nulls)); + + j = 0; + values[j++] = Int64GetDatum((int64) bitmapblkno); + values[j++] = Int32GetDatum(bitmapbit); + values[j++] = BoolGetDatum(bit); + + tuple = heap_form_tuple(tupleDesc, values, nulls); + + PG_RETURN_DATUM(HeapTupleGetDatum(tuple)); +} + +/* ------------------------------------------------ + * hash_metapage_info() + * + * Get the meta-page information for a hash index + * + * Usage: SELECT * FROM hash_metapage_info(get_raw_page('con_hash_index', 0)) + * ------------------------------------------------ + */ +Datum +hash_metapage_info(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + Page page; + HashMetaPageData *metad; + TupleDesc tupleDesc; + HeapTuple tuple; + int i, + j; + Datum values[16]; + bool nulls[16]; + Datum spares[HASH_MAX_SPLITPOINTS]; + Datum mapp[HASH_MAX_BITMAPS]; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + page = verify_hash_page(raw_page, LH_META_PAGE); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + tupleDesc = BlessTupleDesc(tupleDesc); + + metad = HashPageGetMeta(page); + + MemSet(nulls, 0, sizeof(nulls)); + + j = 0; + values[j++] = Int64GetDatum((int64) metad->hashm_magic); + values[j++] = Int64GetDatum((int64) metad->hashm_version); + values[j++] = Float8GetDatum(metad->hashm_ntuples); + values[j++] = Int32GetDatum((int32) metad->hashm_ffactor); + values[j++] = Int32GetDatum((int32) metad->hashm_bsize); + values[j++] = Int32GetDatum((int32) metad->hashm_bmsize); + values[j++] = Int32GetDatum((int32) metad->hashm_bmshift); + values[j++] = Int64GetDatum((int64) metad->hashm_maxbucket); + values[j++] = Int64GetDatum((int64) metad->hashm_highmask); + values[j++] = Int64GetDatum((int64) metad->hashm_lowmask); + values[j++] = Int64GetDatum((int64) metad->hashm_ovflpoint); + values[j++] = Int64GetDatum((int64) metad->hashm_firstfree); + values[j++] = Int64GetDatum((int64) metad->hashm_nmaps); + values[j++] = ObjectIdGetDatum((Oid) metad->hashm_procid); + + for (i = 0; i < HASH_MAX_SPLITPOINTS; i++) + spares[i] = Int64GetDatum((int64) metad->hashm_spares[i]); + values[j++] = PointerGetDatum(construct_array(spares, + HASH_MAX_SPLITPOINTS, + INT8OID, + sizeof(int64), + FLOAT8PASSBYVAL, + TYPALIGN_DOUBLE)); + + for (i = 0; i < HASH_MAX_BITMAPS; i++) + mapp[i] = Int64GetDatum((int64) metad->hashm_mapp[i]); + values[j++] = PointerGetDatum(construct_array(mapp, + HASH_MAX_BITMAPS, + INT8OID, + sizeof(int64), + FLOAT8PASSBYVAL, + TYPALIGN_DOUBLE)); + + tuple = heap_form_tuple(tupleDesc, values, nulls); + + PG_RETURN_DATUM(HeapTupleGetDatum(tuple)); +} diff --git a/contrib/pageinspect/heapfuncs.c b/contrib/pageinspect/heapfuncs.c new file mode 100644 index 0000000..f6760eb --- /dev/null +++ b/contrib/pageinspect/heapfuncs.c @@ -0,0 +1,622 @@ +/*------------------------------------------------------------------------- + * + * heapfuncs.c + * Functions to investigate heap pages + * + * We check the input to these functions for corrupt pointers etc. that + * might cause crashes, but at the same time we try to print out as much + * information as possible, even if it's nonsense. That's because if a + * page is corrupt, we don't know why and how exactly it is corrupt, so we + * let the user judge it. + * + * These functions are restricted to superusers for the fear of introducing + * security holes if the input checking isn't as water-tight as it should be. + * You'd need to be superuser to obtain a raw page image anyway, so + * there's hardly any use case for using these without superuser-rights + * anyway. + * + * Copyright (c) 2007-2021, PostgreSQL Global Development Group + * + * IDENTIFICATION + * contrib/pageinspect/heapfuncs.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "access/htup_details.h" +#include "access/relation.h" +#include "catalog/pg_am_d.h" +#include "catalog/pg_type.h" +#include "funcapi.h" +#include "mb/pg_wchar.h" +#include "miscadmin.h" +#include "pageinspect.h" +#include "port/pg_bitutils.h" +#include "utils/array.h" +#include "utils/builtins.h" +#include "utils/rel.h" + +/* + * It's not supported to create tuples with oids anymore, but when pg_upgrade + * was used to upgrade from an older version, tuples might still have an + * oid. Seems worthwhile to display that. + */ +#define HeapTupleHeaderGetOidOld(tup) \ +( \ + ((tup)->t_infomask & HEAP_HASOID_OLD) ? \ + *((Oid *) ((char *)(tup) + (tup)->t_hoff - sizeof(Oid))) \ + : \ + InvalidOid \ +) + + +/* + * bits_to_text + * + * Converts a bits8-array of 'len' bits to a human-readable + * c-string representation. + */ +static char * +bits_to_text(bits8 *bits, int len) +{ + int i; + char *str; + + str = palloc(len + 1); + + for (i = 0; i < len; i++) + str[i] = (bits[(i / 8)] & (1 << (i % 8))) ? '1' : '0'; + + str[i] = '\0'; + + return str; +} + + +/* + * text_to_bits + * + * Converts a c-string representation of bits into a bits8-array. This is + * the reverse operation of previous routine. + */ +static bits8 * +text_to_bits(char *str, int len) +{ + bits8 *bits; + int off = 0; + char byte = 0; + + bits = palloc(len + 1); + + while (off < len) + { + if (off % 8 == 0) + byte = 0; + + if ((str[off] == '0') || (str[off] == '1')) + byte = byte | ((str[off] - '0') << off % 8); + else + ereport(ERROR, + (errcode(ERRCODE_DATA_CORRUPTED), + errmsg("invalid character \"%.*s\" in t_bits string", + pg_mblen(str + off), str + off))); + + if (off % 8 == 7) + bits[off / 8] = byte; + + off++; + } + + return bits; +} + +/* + * heap_page_items + * + * Allows inspection of line pointers and tuple headers of a heap page. + */ +PG_FUNCTION_INFO_V1(heap_page_items); + +typedef struct heap_page_items_state +{ + TupleDesc tupd; + Page page; + uint16 offset; +} heap_page_items_state; + +Datum +heap_page_items(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + heap_page_items_state *inter_call_data = NULL; + FuncCallContext *fctx; + int raw_page_size; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + raw_page_size = VARSIZE(raw_page) - VARHDRSZ; + + if (SRF_IS_FIRSTCALL()) + { + TupleDesc tupdesc; + MemoryContext mctx; + + if (raw_page_size < SizeOfPageHeaderData) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page too small (%d bytes)", raw_page_size))); + + fctx = SRF_FIRSTCALL_INIT(); + mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx); + + inter_call_data = palloc(sizeof(heap_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->tupd = tupdesc; + + inter_call_data->offset = FirstOffsetNumber; + inter_call_data->page = VARDATA(raw_page); + + fctx->max_calls = PageGetMaxOffsetNumber(inter_call_data->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; + HeapTuple resultTuple; + Datum result; + ItemId id; + Datum values[14]; + bool nulls[14]; + uint16 lp_offset; + uint16 lp_flags; + uint16 lp_len; + + memset(nulls, 0, sizeof(nulls)); + + /* Extract information from the line pointer */ + + id = PageGetItemId(page, inter_call_data->offset); + + lp_offset = ItemIdGetOffset(id); + lp_flags = ItemIdGetFlags(id); + lp_len = ItemIdGetLength(id); + + values[0] = UInt16GetDatum(inter_call_data->offset); + values[1] = UInt16GetDatum(lp_offset); + values[2] = UInt16GetDatum(lp_flags); + values[3] = UInt16GetDatum(lp_len); + + /* + * We do just enough validity checking to make sure we don't reference + * data outside the page passed to us. The page could be corrupt in + * many other ways, but at least we won't crash. + */ + if (ItemIdHasStorage(id) && + lp_len >= MinHeapTupleSize && + lp_offset == MAXALIGN(lp_offset) && + lp_offset + lp_len <= raw_page_size) + { + HeapTupleHeader tuphdr; + bytea *tuple_data_bytea; + int tuple_data_len; + + /* Extract information from the tuple header */ + + tuphdr = (HeapTupleHeader) PageGetItem(page, id); + + values[4] = UInt32GetDatum(HeapTupleHeaderGetRawXmin(tuphdr)); + values[5] = UInt32GetDatum(HeapTupleHeaderGetRawXmax(tuphdr)); + /* shared with xvac */ + values[6] = UInt32GetDatum(HeapTupleHeaderGetRawCommandId(tuphdr)); + values[7] = PointerGetDatum(&tuphdr->t_ctid); + values[8] = UInt32GetDatum(tuphdr->t_infomask2); + values[9] = UInt32GetDatum(tuphdr->t_infomask); + values[10] = UInt8GetDatum(tuphdr->t_hoff); + + /* Copy raw tuple data into bytea attribute */ + tuple_data_len = lp_len - tuphdr->t_hoff; + tuple_data_bytea = (bytea *) palloc(tuple_data_len + VARHDRSZ); + SET_VARSIZE(tuple_data_bytea, tuple_data_len + VARHDRSZ); + memcpy(VARDATA(tuple_data_bytea), (char *) tuphdr + tuphdr->t_hoff, + tuple_data_len); + values[13] = PointerGetDatum(tuple_data_bytea); + + /* + * We already checked that the item is completely within the raw + * page passed to us, with the length given in the line pointer. + * Let's check that t_hoff doesn't point over lp_len, before using + * it to access t_bits and oid. + */ + if (tuphdr->t_hoff >= SizeofHeapTupleHeader && + tuphdr->t_hoff <= lp_len && + tuphdr->t_hoff == MAXALIGN(tuphdr->t_hoff)) + { + if (tuphdr->t_infomask & HEAP_HASNULL) + { + int bits_len; + + bits_len = + BITMAPLEN(HeapTupleHeaderGetNatts(tuphdr)) * BITS_PER_BYTE; + values[11] = CStringGetTextDatum(bits_to_text(tuphdr->t_bits, bits_len)); + } + else + nulls[11] = true; + + if (tuphdr->t_infomask & HEAP_HASOID_OLD) + values[12] = HeapTupleHeaderGetOidOld(tuphdr); + else + nulls[12] = true; + } + else + { + nulls[11] = true; + nulls[12] = true; + } + } + else + { + /* + * The line pointer is not used, or it's invalid. Set the rest of + * the fields to NULL + */ + int i; + + for (i = 4; i <= 13; i++) + nulls[i] = true; + } + + /* 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); + } + else + SRF_RETURN_DONE(fctx); +} + +/* + * tuple_data_split_internal + * + * Split raw tuple data taken directly from a page into an array of bytea + * elements. This routine does a lookup on NULL values and creates array + * elements accordingly. This is a reimplementation of nocachegetattr() + * in heaptuple.c simplified for educational purposes. + */ +static Datum +tuple_data_split_internal(Oid relid, char *tupdata, + uint16 tupdata_len, uint16 t_infomask, + uint16 t_infomask2, bits8 *t_bits, + bool do_detoast) +{ + ArrayBuildState *raw_attrs; + int nattrs; + int i; + int off = 0; + Relation rel; + TupleDesc tupdesc; + + /* Get tuple descriptor from relation OID */ + rel = relation_open(relid, AccessShareLock); + tupdesc = RelationGetDescr(rel); + + raw_attrs = initArrayResult(BYTEAOID, CurrentMemoryContext, false); + nattrs = tupdesc->natts; + + if (rel->rd_rel->relam != HEAP_TABLE_AM_OID) + ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("only heap AM is supported"))); + + if (nattrs < (t_infomask2 & HEAP_NATTS_MASK)) + ereport(ERROR, + (errcode(ERRCODE_DATA_CORRUPTED), + errmsg("number of attributes in tuple header is greater than number of attributes in tuple descriptor"))); + + for (i = 0; i < nattrs; i++) + { + Form_pg_attribute attr; + bool is_null; + bytea *attr_data = NULL; + + attr = TupleDescAttr(tupdesc, i); + + /* + * Tuple header can specify fewer attributes than tuple descriptor as + * ALTER TABLE ADD COLUMN without DEFAULT keyword does not actually + * change tuples in pages, so attributes with numbers greater than + * (t_infomask2 & HEAP_NATTS_MASK) should be treated as NULL. + */ + if (i >= (t_infomask2 & HEAP_NATTS_MASK)) + is_null = true; + else + is_null = (t_infomask & HEAP_HASNULL) && att_isnull(i, t_bits); + + if (!is_null) + { + int len; + + if (attr->attlen == -1) + { + off = att_align_pointer(off, attr->attalign, -1, + tupdata + off); + + /* + * As VARSIZE_ANY throws an exception if it can't properly + * detect the type of external storage in macros VARTAG_SIZE, + * this check is repeated to have a nicer error handling. + */ + if (VARATT_IS_EXTERNAL(tupdata + off) && + !VARATT_IS_EXTERNAL_ONDISK(tupdata + off) && + !VARATT_IS_EXTERNAL_INDIRECT(tupdata + off)) + ereport(ERROR, + (errcode(ERRCODE_DATA_CORRUPTED), + errmsg("first byte of varlena attribute is incorrect for attribute %d", i))); + + len = VARSIZE_ANY(tupdata + off); + } + else + { + off = att_align_nominal(off, attr->attalign); + len = attr->attlen; + } + + if (tupdata_len < off + len) + ereport(ERROR, + (errcode(ERRCODE_DATA_CORRUPTED), + errmsg("unexpected end of tuple data"))); + + if (attr->attlen == -1 && do_detoast) + attr_data = DatumGetByteaPCopy(tupdata + off); + else + { + attr_data = (bytea *) palloc(len + VARHDRSZ); + SET_VARSIZE(attr_data, len + VARHDRSZ); + memcpy(VARDATA(attr_data), tupdata + off, len); + } + + off = att_addlength_pointer(off, attr->attlen, + tupdata + off); + } + + raw_attrs = accumArrayResult(raw_attrs, PointerGetDatum(attr_data), + is_null, BYTEAOID, CurrentMemoryContext); + if (attr_data) + pfree(attr_data); + } + + if (tupdata_len != off) + ereport(ERROR, + (errcode(ERRCODE_DATA_CORRUPTED), + errmsg("end of tuple reached without looking at all its data"))); + + relation_close(rel, AccessShareLock); + + return makeArrayResult(raw_attrs, CurrentMemoryContext); +} + +/* + * tuple_data_split + * + * Split raw tuple data taken directly from page into distinct elements + * taking into account null values. + */ +PG_FUNCTION_INFO_V1(tuple_data_split); + +Datum +tuple_data_split(PG_FUNCTION_ARGS) +{ + Oid relid; + bytea *raw_data; + uint16 t_infomask; + uint16 t_infomask2; + char *t_bits_str; + bool do_detoast = false; + bits8 *t_bits = NULL; + Datum res; + + relid = PG_GETARG_OID(0); + raw_data = PG_ARGISNULL(1) ? NULL : PG_GETARG_BYTEA_P(1); + t_infomask = PG_GETARG_INT16(2); + t_infomask2 = PG_GETARG_INT16(3); + t_bits_str = PG_ARGISNULL(4) ? NULL : + text_to_cstring(PG_GETARG_TEXT_PP(4)); + + if (PG_NARGS() >= 6) + do_detoast = PG_GETARG_BOOL(5); + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + if (!raw_data) + PG_RETURN_NULL(); + + /* + * Convert t_bits string back to the bits8 array as represented in the + * tuple header. + */ + if (t_infomask & HEAP_HASNULL) + { + int bits_str_len; + int bits_len; + + bits_len = BITMAPLEN(t_infomask2 & HEAP_NATTS_MASK) * BITS_PER_BYTE; + if (!t_bits_str) + ereport(ERROR, + (errcode(ERRCODE_DATA_CORRUPTED), + errmsg("t_bits string must not be NULL"))); + + bits_str_len = strlen(t_bits_str); + if (bits_len != bits_str_len) + ereport(ERROR, + (errcode(ERRCODE_DATA_CORRUPTED), + errmsg("unexpected length of t_bits string: %u, expected %u", + bits_str_len, bits_len))); + + /* do the conversion */ + t_bits = text_to_bits(t_bits_str, bits_str_len); + } + else + { + if (t_bits_str) + ereport(ERROR, + (errcode(ERRCODE_DATA_CORRUPTED), + errmsg("t_bits string is expected to be NULL, but instead it is %zu bytes long", + strlen(t_bits_str)))); + } + + /* Split tuple data */ + res = tuple_data_split_internal(relid, (char *) raw_data + VARHDRSZ, + VARSIZE(raw_data) - VARHDRSZ, + t_infomask, t_infomask2, t_bits, + do_detoast); + + if (t_bits) + pfree(t_bits); + + PG_RETURN_ARRAYTYPE_P(res); +} + +/* + * heap_tuple_infomask_flags + * + * Decode into a human-readable format t_infomask and t_infomask2 associated + * to a tuple. All the flags are described in access/htup_details.h. + */ +PG_FUNCTION_INFO_V1(heap_tuple_infomask_flags); + +Datum +heap_tuple_infomask_flags(PG_FUNCTION_ARGS) +{ +#define HEAP_TUPLE_INFOMASK_COLS 2 + Datum values[HEAP_TUPLE_INFOMASK_COLS]; + bool nulls[HEAP_TUPLE_INFOMASK_COLS]; + uint16 t_infomask = PG_GETARG_INT16(0); + uint16 t_infomask2 = PG_GETARG_INT16(1); + int cnt = 0; + ArrayType *a; + int bitcnt; + Datum *flags; + TupleDesc tupdesc; + HeapTuple tuple; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + /* 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"); + + bitcnt = pg_popcount((const char *) &t_infomask, sizeof(uint16)) + + pg_popcount((const char *) &t_infomask2, sizeof(uint16)); + + /* Initialize values and NULL flags arrays */ + MemSet(values, 0, sizeof(values)); + MemSet(nulls, 0, sizeof(nulls)); + + /* If no flags, return a set of empty arrays */ + if (bitcnt <= 0) + { + values[0] = PointerGetDatum(construct_empty_array(TEXTOID)); + values[1] = PointerGetDatum(construct_empty_array(TEXTOID)); + tuple = heap_form_tuple(tupdesc, values, nulls); + PG_RETURN_DATUM(HeapTupleGetDatum(tuple)); + } + + /* build set of raw flags */ + flags = (Datum *) palloc0(sizeof(Datum) * bitcnt); + + /* decode t_infomask */ + if ((t_infomask & HEAP_HASNULL) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_HASNULL"); + if ((t_infomask & HEAP_HASVARWIDTH) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_HASVARWIDTH"); + if ((t_infomask & HEAP_HASEXTERNAL) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_HASEXTERNAL"); + if ((t_infomask & HEAP_HASOID_OLD) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_HASOID_OLD"); + if ((t_infomask & HEAP_XMAX_KEYSHR_LOCK) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_XMAX_KEYSHR_LOCK"); + if ((t_infomask & HEAP_COMBOCID) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_COMBOCID"); + if ((t_infomask & HEAP_XMAX_EXCL_LOCK) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_XMAX_EXCL_LOCK"); + if ((t_infomask & HEAP_XMAX_LOCK_ONLY) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_XMAX_LOCK_ONLY"); + if ((t_infomask & HEAP_XMIN_COMMITTED) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_XMIN_COMMITTED"); + if ((t_infomask & HEAP_XMIN_INVALID) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_XMIN_INVALID"); + if ((t_infomask & HEAP_XMAX_COMMITTED) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_XMAX_COMMITTED"); + if ((t_infomask & HEAP_XMAX_INVALID) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_XMAX_INVALID"); + if ((t_infomask & HEAP_XMAX_IS_MULTI) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_XMAX_IS_MULTI"); + if ((t_infomask & HEAP_UPDATED) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_UPDATED"); + if ((t_infomask & HEAP_MOVED_OFF) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_MOVED_OFF"); + if ((t_infomask & HEAP_MOVED_IN) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_MOVED_IN"); + + /* decode t_infomask2 */ + if ((t_infomask2 & HEAP_KEYS_UPDATED) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_KEYS_UPDATED"); + if ((t_infomask2 & HEAP_HOT_UPDATED) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_HOT_UPDATED"); + if ((t_infomask2 & HEAP_ONLY_TUPLE) != 0) + flags[cnt++] = CStringGetTextDatum("HEAP_ONLY_TUPLE"); + + /* build value */ + Assert(cnt <= bitcnt); + a = construct_array(flags, cnt, TEXTOID, -1, false, TYPALIGN_INT); + values[0] = PointerGetDatum(a); + + /* + * Build set of combined flags. Use the same array as previously, this + * keeps the code simple. + */ + cnt = 0; + MemSet(flags, 0, sizeof(Datum) * bitcnt); + + /* decode combined masks of t_infomask */ + if ((t_infomask & HEAP_XMAX_SHR_LOCK) == HEAP_XMAX_SHR_LOCK) + flags[cnt++] = CStringGetTextDatum("HEAP_XMAX_SHR_LOCK"); + if ((t_infomask & HEAP_XMIN_FROZEN) == HEAP_XMIN_FROZEN) + flags[cnt++] = CStringGetTextDatum("HEAP_XMIN_FROZEN"); + if ((t_infomask & HEAP_MOVED) == HEAP_MOVED) + flags[cnt++] = CStringGetTextDatum("HEAP_MOVED"); + + /* Build an empty array if there are no combined flags */ + if (cnt == 0) + a = construct_empty_array(TEXTOID); + else + a = construct_array(flags, cnt, TEXTOID, -1, false, TYPALIGN_INT); + pfree(flags); + values[1] = PointerGetDatum(a); + + /* Returns the record as Datum */ + tuple = heap_form_tuple(tupdesc, values, nulls); + PG_RETURN_DATUM(HeapTupleGetDatum(tuple)); +} diff --git a/contrib/pageinspect/pageinspect--1.0--1.1.sql b/contrib/pageinspect/pageinspect--1.0--1.1.sql new file mode 100644 index 0000000..0e2c3f4 --- /dev/null +++ b/contrib/pageinspect/pageinspect--1.0--1.1.sql @@ -0,0 +1,18 @@ +/* contrib/pageinspect/pageinspect--1.0--1.1.sql */ + +-- complain if script is sourced in psql, rather than via ALTER EXTENSION +\echo Use "ALTER EXTENSION pageinspect UPDATE TO '1.1'" to load this file. \quit + +DROP FUNCTION page_header(bytea); +CREATE FUNCTION page_header(IN page bytea, + OUT lsn text, + OUT checksum smallint, + OUT flags smallint, + OUT lower smallint, + OUT upper smallint, + OUT special smallint, + OUT pagesize smallint, + OUT version smallint, + OUT prune_xid xid) +AS 'MODULE_PATHNAME', 'page_header' +LANGUAGE C STRICT; diff --git a/contrib/pageinspect/pageinspect--1.1--1.2.sql b/contrib/pageinspect/pageinspect--1.1--1.2.sql new file mode 100644 index 0000000..31ffbb0 --- /dev/null +++ b/contrib/pageinspect/pageinspect--1.1--1.2.sql @@ -0,0 +1,18 @@ +/* contrib/pageinspect/pageinspect--1.1--1.2.sql */ + +-- complain if script is sourced in psql, rather than via ALTER EXTENSION +\echo Use "ALTER EXTENSION pageinspect UPDATE TO '1.2'" to load this file. \quit + +DROP FUNCTION page_header(bytea); +CREATE FUNCTION page_header(IN page bytea, + OUT lsn pg_lsn, + OUT checksum smallint, + OUT flags smallint, + OUT lower smallint, + OUT upper smallint, + OUT special smallint, + OUT pagesize smallint, + OUT version smallint, + OUT prune_xid xid) +AS 'MODULE_PATHNAME', 'page_header' +LANGUAGE C STRICT; diff --git a/contrib/pageinspect/pageinspect--1.2--1.3.sql b/contrib/pageinspect/pageinspect--1.2--1.3.sql new file mode 100644 index 0000000..9c55a6e --- /dev/null +++ b/contrib/pageinspect/pageinspect--1.2--1.3.sql @@ -0,0 +1,82 @@ +/* contrib/pageinspect/pageinspect--1.2--1.3.sql */ + +-- complain if script is sourced in psql, rather than via ALTER EXTENSION +\echo Use "ALTER EXTENSION pageinspect UPDATE TO '1.3'" to load this file. \quit + +-- +-- brin_page_type() +-- +CREATE FUNCTION brin_page_type(IN page bytea) +RETURNS text +AS 'MODULE_PATHNAME', 'brin_page_type' +LANGUAGE C STRICT; + +-- +-- brin_metapage_info() +-- +CREATE FUNCTION brin_metapage_info(IN page bytea, OUT magic text, + OUT version integer, OUT pagesperrange integer, OUT lastrevmappage bigint) +AS 'MODULE_PATHNAME', 'brin_metapage_info' +LANGUAGE C STRICT; + +-- +-- brin_revmap_data() +-- +CREATE FUNCTION brin_revmap_data(IN page bytea, + OUT pages tid) +RETURNS SETOF tid +AS 'MODULE_PATHNAME', 'brin_revmap_data' +LANGUAGE C STRICT; + +-- +-- brin_page_items() +-- +CREATE FUNCTION brin_page_items(IN page bytea, IN index_oid regclass, + OUT itemoffset int, + OUT blknum int, + OUT attnum int, + OUT allnulls bool, + OUT hasnulls bool, + OUT placeholder bool, + OUT value text) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'brin_page_items' +LANGUAGE C STRICT; + +-- +-- gin_metapage_info() +-- +CREATE FUNCTION gin_metapage_info(IN page bytea, + OUT pending_head bigint, + OUT pending_tail bigint, + OUT tail_free_size int4, + OUT n_pending_pages bigint, + OUT n_pending_tuples bigint, + OUT n_total_pages bigint, + OUT n_entry_pages bigint, + OUT n_data_pages bigint, + OUT n_entries bigint, + OUT version int4) +AS 'MODULE_PATHNAME', 'gin_metapage_info' +LANGUAGE C STRICT; + +-- +-- gin_page_opaque_info() +-- +CREATE FUNCTION gin_page_opaque_info(IN page bytea, + OUT rightlink bigint, + OUT maxoff int4, + OUT flags text[]) +AS 'MODULE_PATHNAME', 'gin_page_opaque_info' +LANGUAGE C STRICT; + +-- +-- gin_leafpage_items() +-- +CREATE FUNCTION gin_leafpage_items(IN page bytea, + OUT first_tid tid, + OUT nbytes int2, + OUT tids tid[]) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'gin_leafpage_items' +LANGUAGE C STRICT; diff --git a/contrib/pageinspect/pageinspect--1.3--1.4.sql b/contrib/pageinspect/pageinspect--1.3--1.4.sql new file mode 100644 index 0000000..86e0dfa --- /dev/null +++ b/contrib/pageinspect/pageinspect--1.3--1.4.sql @@ -0,0 +1,118 @@ +/* contrib/pageinspect/pageinspect--1.3--1.4.sql */ + +-- complain if script is sourced in psql, rather than via ALTER EXTENSION +\echo Use "ALTER EXTENSION pageinspect UPDATE TO '1.4'" to load this file. \quit + +-- +-- heap_page_items() +-- +DROP FUNCTION heap_page_items(bytea); +CREATE FUNCTION heap_page_items(IN page bytea, + OUT lp smallint, + OUT lp_off smallint, + OUT lp_flags smallint, + OUT lp_len smallint, + OUT t_xmin xid, + OUT t_xmax xid, + OUT t_field3 int4, + OUT t_ctid tid, + OUT t_infomask2 integer, + OUT t_infomask integer, + OUT t_hoff smallint, + OUT t_bits text, + OUT t_oid oid, + OUT t_data bytea) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'heap_page_items' +LANGUAGE C STRICT; + +-- +-- tuple_data_split() +-- +CREATE FUNCTION tuple_data_split(rel_oid oid, + t_data bytea, + t_infomask integer, + t_infomask2 integer, + t_bits text) +RETURNS bytea[] +AS 'MODULE_PATHNAME','tuple_data_split' +LANGUAGE C; + +CREATE FUNCTION tuple_data_split(rel_oid oid, + t_data bytea, + t_infomask integer, + t_infomask2 integer, + t_bits text, + do_detoast bool) +RETURNS bytea[] +AS 'MODULE_PATHNAME','tuple_data_split' +LANGUAGE C; + +-- +-- heap_page_item_attrs() +-- +CREATE FUNCTION heap_page_item_attrs( + IN page bytea, + IN rel_oid regclass, + IN do_detoast bool, + OUT lp smallint, + OUT lp_off smallint, + OUT lp_flags smallint, + OUT lp_len smallint, + OUT t_xmin xid, + OUT t_xmax xid, + OUT t_field3 int4, + OUT t_ctid tid, + OUT t_infomask2 integer, + OUT t_infomask integer, + OUT t_hoff smallint, + OUT t_bits text, + OUT t_oid oid, + OUT t_attrs bytea[] + ) +RETURNS SETOF record AS $$ +SELECT lp, + lp_off, + lp_flags, + lp_len, + t_xmin, + t_xmax, + t_field3, + t_ctid, + t_infomask2, + t_infomask, + t_hoff, + t_bits, + t_oid, + tuple_data_split( + rel_oid, + t_data, + t_infomask, + t_infomask2, + t_bits, + do_detoast) + AS t_attrs + FROM heap_page_items(page); +$$ LANGUAGE SQL; + +CREATE FUNCTION heap_page_item_attrs( + IN page bytea, + IN rel_oid regclass, + OUT lp smallint, + OUT lp_off smallint, + OUT lp_flags smallint, + OUT lp_len smallint, + OUT t_xmin xid, + OUT t_xmax xid, + OUT t_field3 int4, + OUT t_ctid tid, + OUT t_infomask2 integer, + OUT t_infomask integer, + OUT t_hoff smallint, + OUT t_bits text, + OUT t_oid oid, + OUT t_attrs bytea[] + ) +RETURNS SETOF record AS $$ +SELECT * from heap_page_item_attrs(page, rel_oid, false); +$$ LANGUAGE SQL; diff --git a/contrib/pageinspect/pageinspect--1.4--1.5.sql b/contrib/pageinspect/pageinspect--1.4--1.5.sql new file mode 100644 index 0000000..7ed7b54 --- /dev/null +++ b/contrib/pageinspect/pageinspect--1.4--1.5.sql @@ -0,0 +1,24 @@ +/* contrib/pageinspect/pageinspect--1.4--1.5.sql */ + +-- complain if script is sourced in psql, rather than via ALTER EXTENSION +\echo Use "ALTER EXTENSION pageinspect UPDATE TO '1.5'" to load this file. \quit + +ALTER FUNCTION get_raw_page(text, int4) PARALLEL SAFE; +ALTER FUNCTION get_raw_page(text, text, int4) PARALLEL SAFE; +ALTER FUNCTION page_header(bytea) PARALLEL SAFE; +ALTER FUNCTION heap_page_items(bytea) PARALLEL SAFE; +ALTER FUNCTION tuple_data_split(oid, bytea, integer, integer, text) PARALLEL SAFE; +ALTER FUNCTION tuple_data_split(oid, bytea, integer, integer, text, bool) PARALLEL SAFE; +ALTER FUNCTION heap_page_item_attrs(bytea, regclass, bool) PARALLEL SAFE; +ALTER FUNCTION heap_page_item_attrs(bytea, regclass) PARALLEL SAFE; +ALTER FUNCTION bt_metap(text) PARALLEL SAFE; +ALTER FUNCTION bt_page_stats(text, int4) PARALLEL SAFE; +ALTER FUNCTION bt_page_items(text, int4) PARALLEL SAFE; +ALTER FUNCTION brin_page_type(bytea) PARALLEL SAFE; +ALTER FUNCTION brin_metapage_info(bytea) PARALLEL SAFE; +ALTER FUNCTION brin_revmap_data(bytea) PARALLEL SAFE; +ALTER FUNCTION brin_page_items(bytea, regclass) PARALLEL SAFE; +ALTER FUNCTION fsm_page_contents(bytea) PARALLEL SAFE; +ALTER FUNCTION gin_metapage_info(bytea) PARALLEL SAFE; +ALTER FUNCTION gin_page_opaque_info(bytea) PARALLEL SAFE; +ALTER FUNCTION gin_leafpage_items(bytea) PARALLEL SAFE; diff --git a/contrib/pageinspect/pageinspect--1.5--1.6.sql b/contrib/pageinspect/pageinspect--1.5--1.6.sql new file mode 100644 index 0000000..c435628 --- /dev/null +++ b/contrib/pageinspect/pageinspect--1.5--1.6.sql @@ -0,0 +1,99 @@ +/* contrib/pageinspect/pageinspect--1.5--1.6.sql */ + +-- complain if script is sourced in psql, rather than via ALTER EXTENSION +\echo Use "ALTER EXTENSION pageinspect UPDATE TO '1.6'" to load this file. \quit + +-- +-- HASH functions +-- + +-- +-- hash_page_type() +-- +CREATE FUNCTION hash_page_type(IN page bytea) +RETURNS text +AS 'MODULE_PATHNAME', 'hash_page_type' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- hash_page_stats() +-- +CREATE FUNCTION hash_page_stats(IN page bytea, + OUT live_items int4, + OUT dead_items int4, + OUT page_size int4, + OUT free_size int4, + OUT hasho_prevblkno int8, + OUT hasho_nextblkno int8, + OUT hasho_bucket int8, + OUT hasho_flag int4, + OUT hasho_page_id int4) +AS 'MODULE_PATHNAME', 'hash_page_stats' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- hash_page_items() +-- +CREATE FUNCTION hash_page_items(IN page bytea, + OUT itemoffset int4, + OUT ctid tid, + OUT data int8) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'hash_page_items' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- hash_bitmap_info() +-- +CREATE FUNCTION hash_bitmap_info(IN index_oid regclass, IN blkno int8, + OUT bitmapblkno int8, + OUT bitmapbit int4, + OUT bitstatus bool) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'hash_bitmap_info' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- hash_metapage_info() +-- +CREATE FUNCTION hash_metapage_info(IN page bytea, + OUT magic int8, + OUT version int8, + OUT ntuples double precision, + OUT ffactor int4, + OUT bsize int4, + OUT bmsize int4, + OUT bmshift int4, + OUT maxbucket int8, + OUT highmask int8, + OUT lowmask int8, + OUT ovflpoint int8, + OUT firstfree int8, + OUT nmaps int8, + OUT procid oid, + OUT spares int8[], + OUT mapp int8[]) +AS 'MODULE_PATHNAME', 'hash_metapage_info' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- page_checksum() +-- +CREATE FUNCTION page_checksum(IN page bytea, IN blkno int4) +RETURNS smallint +AS 'MODULE_PATHNAME', 'page_checksum' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- bt_page_items_bytea() +-- +CREATE FUNCTION bt_page_items(IN page bytea, + OUT itemoffset smallint, + OUT ctid tid, + OUT itemlen smallint, + OUT nulls bool, + OUT vars bool, + OUT data text) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'bt_page_items_bytea' +LANGUAGE C STRICT PARALLEL SAFE; diff --git a/contrib/pageinspect/pageinspect--1.5.sql b/contrib/pageinspect/pageinspect--1.5.sql new file mode 100644 index 0000000..1e40c3c --- /dev/null +++ b/contrib/pageinspect/pageinspect--1.5.sql @@ -0,0 +1,279 @@ +/* contrib/pageinspect/pageinspect--1.5.sql */ + +-- complain if script is sourced in psql, rather than via CREATE EXTENSION +\echo Use "CREATE EXTENSION pageinspect" to load this file. \quit + +-- +-- get_raw_page() +-- +CREATE FUNCTION get_raw_page(text, int4) +RETURNS bytea +AS 'MODULE_PATHNAME', 'get_raw_page' +LANGUAGE C STRICT PARALLEL SAFE; + +CREATE FUNCTION get_raw_page(text, text, int4) +RETURNS bytea +AS 'MODULE_PATHNAME', 'get_raw_page_fork' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- page_header() +-- +CREATE FUNCTION page_header(IN page bytea, + OUT lsn pg_lsn, + OUT checksum smallint, + OUT flags smallint, + OUT lower smallint, + OUT upper smallint, + OUT special smallint, + OUT pagesize smallint, + OUT version smallint, + OUT prune_xid xid) +AS 'MODULE_PATHNAME', 'page_header' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- heap_page_items() +-- +CREATE FUNCTION heap_page_items(IN page bytea, + OUT lp smallint, + OUT lp_off smallint, + OUT lp_flags smallint, + OUT lp_len smallint, + OUT t_xmin xid, + OUT t_xmax xid, + OUT t_field3 int4, + OUT t_ctid tid, + OUT t_infomask2 integer, + OUT t_infomask integer, + OUT t_hoff smallint, + OUT t_bits text, + OUT t_oid oid, + OUT t_data bytea) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'heap_page_items' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- tuple_data_split() +-- +CREATE FUNCTION tuple_data_split(rel_oid oid, + t_data bytea, + t_infomask integer, + t_infomask2 integer, + t_bits text) +RETURNS bytea[] +AS 'MODULE_PATHNAME','tuple_data_split' +LANGUAGE C PARALLEL SAFE; + +CREATE FUNCTION tuple_data_split(rel_oid oid, + t_data bytea, + t_infomask integer, + t_infomask2 integer, + t_bits text, + do_detoast bool) +RETURNS bytea[] +AS 'MODULE_PATHNAME','tuple_data_split' +LANGUAGE C PARALLEL SAFE; + +-- +-- heap_page_item_attrs() +-- +CREATE FUNCTION heap_page_item_attrs( + IN page bytea, + IN rel_oid regclass, + IN do_detoast bool, + OUT lp smallint, + OUT lp_off smallint, + OUT lp_flags smallint, + OUT lp_len smallint, + OUT t_xmin xid, + OUT t_xmax xid, + OUT t_field3 int4, + OUT t_ctid tid, + OUT t_infomask2 integer, + OUT t_infomask integer, + OUT t_hoff smallint, + OUT t_bits text, + OUT t_oid oid, + OUT t_attrs bytea[] + ) +RETURNS SETOF record AS $$ +SELECT lp, + lp_off, + lp_flags, + lp_len, + t_xmin, + t_xmax, + t_field3, + t_ctid, + t_infomask2, + t_infomask, + t_hoff, + t_bits, + t_oid, + tuple_data_split( + rel_oid, + t_data, + t_infomask, + t_infomask2, + t_bits, + do_detoast) + AS t_attrs + FROM heap_page_items(page); +$$ LANGUAGE SQL PARALLEL SAFE; + +CREATE FUNCTION heap_page_item_attrs(IN page bytea, IN rel_oid regclass, + OUT lp smallint, + OUT lp_off smallint, + OUT lp_flags smallint, + OUT lp_len smallint, + OUT t_xmin xid, + OUT t_xmax xid, + OUT t_field3 int4, + OUT t_ctid tid, + OUT t_infomask2 integer, + OUT t_infomask integer, + OUT t_hoff smallint, + OUT t_bits text, + OUT t_oid oid, + OUT t_attrs bytea[] + ) +RETURNS SETOF record AS $$ +SELECT * from heap_page_item_attrs(page, rel_oid, false); +$$ LANGUAGE SQL PARALLEL SAFE; + +-- +-- bt_metap() +-- +CREATE FUNCTION bt_metap(IN relname text, + OUT magic int4, + OUT version int4, + OUT root int4, + OUT level int4, + OUT fastroot int4, + OUT fastlevel int4) +AS 'MODULE_PATHNAME', 'bt_metap' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- bt_page_stats() +-- +CREATE FUNCTION bt_page_stats(IN relname text, IN blkno int4, + OUT blkno int4, + OUT type "char", + OUT live_items int4, + OUT dead_items int4, + OUT avg_item_size int4, + OUT page_size int4, + OUT free_size int4, + OUT btpo_prev int4, + OUT btpo_next int4, + OUT btpo int4, + OUT btpo_flags int4) +AS 'MODULE_PATHNAME', 'bt_page_stats' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- bt_page_items() +-- +CREATE FUNCTION bt_page_items(IN relname text, IN blkno int4, + OUT itemoffset smallint, + OUT ctid tid, + OUT itemlen smallint, + OUT nulls bool, + OUT vars bool, + OUT data text) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'bt_page_items' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- brin_page_type() +-- +CREATE FUNCTION brin_page_type(IN page bytea) +RETURNS text +AS 'MODULE_PATHNAME', 'brin_page_type' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- brin_metapage_info() +-- +CREATE FUNCTION brin_metapage_info(IN page bytea, OUT magic text, + OUT version integer, OUT pagesperrange integer, OUT lastrevmappage bigint) +AS 'MODULE_PATHNAME', 'brin_metapage_info' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- brin_revmap_data() +-- +CREATE FUNCTION brin_revmap_data(IN page bytea, + OUT pages tid) +RETURNS SETOF tid +AS 'MODULE_PATHNAME', 'brin_revmap_data' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- brin_page_items() +-- +CREATE FUNCTION brin_page_items(IN page bytea, IN index_oid regclass, + OUT itemoffset int, + OUT blknum int, + OUT attnum int, + OUT allnulls bool, + OUT hasnulls bool, + OUT placeholder bool, + OUT value text) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'brin_page_items' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- fsm_page_contents() +-- +CREATE FUNCTION fsm_page_contents(IN page bytea) +RETURNS text +AS 'MODULE_PATHNAME', 'fsm_page_contents' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- GIN functions +-- + +-- +-- gin_metapage_info() +-- +CREATE FUNCTION gin_metapage_info(IN page bytea, + OUT pending_head bigint, + OUT pending_tail bigint, + OUT tail_free_size int4, + OUT n_pending_pages bigint, + OUT n_pending_tuples bigint, + OUT n_total_pages bigint, + OUT n_entry_pages bigint, + OUT n_data_pages bigint, + OUT n_entries bigint, + OUT version int4) +AS 'MODULE_PATHNAME', 'gin_metapage_info' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- gin_page_opaque_info() +-- +CREATE FUNCTION gin_page_opaque_info(IN page bytea, + OUT rightlink bigint, + OUT maxoff int4, + OUT flags text[]) +AS 'MODULE_PATHNAME', 'gin_page_opaque_info' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- gin_leafpage_items() +-- +CREATE FUNCTION gin_leafpage_items(IN page bytea, + OUT first_tid tid, + OUT nbytes int2, + OUT tids tid[]) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'gin_leafpage_items' +LANGUAGE C STRICT PARALLEL SAFE; diff --git a/contrib/pageinspect/pageinspect--1.6--1.7.sql b/contrib/pageinspect/pageinspect--1.6--1.7.sql new file mode 100644 index 0000000..2433a21 --- /dev/null +++ b/contrib/pageinspect/pageinspect--1.6--1.7.sql @@ -0,0 +1,26 @@ +/* contrib/pageinspect/pageinspect--1.6--1.7.sql */ + +-- complain if script is sourced in psql, rather than via ALTER EXTENSION +\echo Use "ALTER EXTENSION pageinspect UPDATE TO '1.7'" to load this file. \quit + +-- +-- bt_metap() +-- +DROP FUNCTION bt_metap(IN relname text, + OUT magic int4, + OUT version int4, + OUT root int4, + OUT level int4, + OUT fastroot int4, + OUT fastlevel int4); +CREATE FUNCTION bt_metap(IN relname text, + OUT magic int4, + OUT version int4, + OUT root int4, + OUT level int4, + OUT fastroot int4, + OUT fastlevel int4, + OUT oldest_xact int4, + OUT last_cleanup_num_tuples real) +AS 'MODULE_PATHNAME', 'bt_metap' +LANGUAGE C STRICT PARALLEL SAFE; diff --git a/contrib/pageinspect/pageinspect--1.7--1.8.sql b/contrib/pageinspect/pageinspect--1.7--1.8.sql new file mode 100644 index 0000000..45031a0 --- /dev/null +++ b/contrib/pageinspect/pageinspect--1.7--1.8.sql @@ -0,0 +1,69 @@ +/* contrib/pageinspect/pageinspect--1.7--1.8.sql */ + +-- complain if script is sourced in psql, rather than via ALTER EXTENSION +\echo Use "ALTER EXTENSION pageinspect UPDATE TO '1.8'" to load this file. \quit + +-- +-- heap_tuple_infomask_flags() +-- +CREATE FUNCTION heap_tuple_infomask_flags( + t_infomask integer, + t_infomask2 integer, + raw_flags OUT text[], + combined_flags OUT text[]) +RETURNS record +AS 'MODULE_PATHNAME', 'heap_tuple_infomask_flags' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- bt_metap() +-- +DROP FUNCTION bt_metap(text); +CREATE FUNCTION bt_metap(IN relname text, + OUT magic int4, + OUT version int4, + OUT root int8, + OUT level int8, + OUT fastroot int8, + OUT fastlevel int8, + OUT oldest_xact xid, + OUT last_cleanup_num_tuples float8, + OUT allequalimage boolean) +AS 'MODULE_PATHNAME', 'bt_metap' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- bt_page_items(text, int4) +-- +DROP FUNCTION bt_page_items(text, int4); +CREATE FUNCTION bt_page_items(IN relname text, IN blkno int4, + OUT itemoffset smallint, + OUT ctid tid, + OUT itemlen smallint, + OUT nulls bool, + OUT vars bool, + OUT data text, + OUT dead boolean, + OUT htid tid, + OUT tids tid[]) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'bt_page_items' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- bt_page_items(bytea) +-- +DROP FUNCTION bt_page_items(bytea); +CREATE FUNCTION bt_page_items(IN page bytea, + OUT itemoffset smallint, + OUT ctid tid, + OUT itemlen smallint, + OUT nulls bool, + OUT vars bool, + OUT data text, + OUT dead boolean, + OUT htid tid, + OUT tids tid[]) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'bt_page_items_bytea' +LANGUAGE C STRICT PARALLEL SAFE; 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 0000000..be89a64 --- /dev/null +++ b/contrib/pageinspect/pageinspect--1.8--1.9.sql @@ -0,0 +1,137 @@ +/* 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_bytea() +-- +CREATE FUNCTION gist_page_items_bytea(IN page bytea, + OUT itemoffset smallint, + OUT ctid tid, + OUT itemlen smallint, + OUT dead boolean, + OUT key_data bytea) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'gist_page_items_bytea' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- gist_page_items() +-- +CREATE FUNCTION gist_page_items(IN page bytea, + IN index_oid regclass, + OUT itemoffset smallint, + OUT ctid tid, + OUT itemlen smallint, + OUT dead boolean, + OUT keys text) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'gist_page_items' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- get_raw_page() +-- +DROP FUNCTION get_raw_page(text, int4); +CREATE FUNCTION get_raw_page(text, int8) +RETURNS bytea +AS 'MODULE_PATHNAME', 'get_raw_page_1_9' +LANGUAGE C STRICT PARALLEL SAFE; + +DROP FUNCTION get_raw_page(text, text, int4); +CREATE FUNCTION get_raw_page(text, text, int8) +RETURNS bytea +AS 'MODULE_PATHNAME', 'get_raw_page_fork_1_9' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- page_checksum() +-- +DROP FUNCTION page_checksum(IN page bytea, IN blkno int4); +CREATE FUNCTION page_checksum(IN page bytea, IN blkno int8) +RETURNS smallint +AS 'MODULE_PATHNAME', 'page_checksum_1_9' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- bt_metap() +-- +DROP FUNCTION bt_metap(text); +CREATE FUNCTION bt_metap(IN relname text, + OUT magic int4, + OUT version int4, + OUT root int8, + OUT level int8, + OUT fastroot int8, + OUT fastlevel int8, + OUT last_cleanup_num_delpages int8, + OUT last_cleanup_num_tuples float8, + OUT allequalimage boolean) +AS 'MODULE_PATHNAME', 'bt_metap' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- bt_page_stats() +-- +DROP FUNCTION bt_page_stats(text, int4); +CREATE FUNCTION bt_page_stats(IN relname text, IN blkno int8, + OUT blkno int8, + OUT type "char", + OUT live_items int4, + OUT dead_items int4, + OUT avg_item_size int4, + OUT page_size int4, + OUT free_size int4, + OUT btpo_prev int8, + OUT btpo_next int8, + OUT btpo_level int8, + OUT btpo_flags int4) +AS 'MODULE_PATHNAME', 'bt_page_stats_1_9' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- bt_page_items() +-- +DROP FUNCTION bt_page_items(text, int4); +CREATE FUNCTION bt_page_items(IN relname text, IN blkno int8, + OUT itemoffset smallint, + OUT ctid tid, + OUT itemlen smallint, + OUT nulls bool, + OUT vars bool, + OUT data text, + OUT dead boolean, + OUT htid tid, + OUT tids tid[]) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'bt_page_items_1_9' +LANGUAGE C STRICT PARALLEL SAFE; + +-- +-- brin_page_items() +-- +DROP FUNCTION brin_page_items(IN page bytea, IN index_oid regclass); +CREATE FUNCTION brin_page_items(IN page bytea, IN index_oid regclass, + OUT itemoffset int, + OUT blknum int8, + OUT attnum int, + OUT allnulls bool, + OUT hasnulls bool, + OUT placeholder bool, + OUT value text) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'brin_page_items' +LANGUAGE C STRICT PARALLEL SAFE; diff --git a/contrib/pageinspect/pageinspect.control b/contrib/pageinspect/pageinspect.control new file mode 100644 index 0000000..bd71676 --- /dev/null +++ b/contrib/pageinspect/pageinspect.control @@ -0,0 +1,5 @@ +# pageinspect extension +comment = 'inspect the contents of database pages at a low level' +default_version = '1.9' +module_pathname = '$libdir/pageinspect' +relocatable = true diff --git a/contrib/pageinspect/pageinspect.h b/contrib/pageinspect/pageinspect.h new file mode 100644 index 0000000..3812a3c --- /dev/null +++ b/contrib/pageinspect/pageinspect.h @@ -0,0 +1,30 @@ +/*------------------------------------------------------------------------- + * + * pageinspect.h + * Common functions for pageinspect. + * + * Copyright (c) 2017-2021, PostgreSQL Global Development Group + * + * IDENTIFICATION + * contrib/pageinspect/pageinspect.h + * + *------------------------------------------------------------------------- + */ +#ifndef _PAGEINSPECT_H_ +#define _PAGEINSPECT_H_ + +#include "storage/bufpage.h" + +/* + * Extension version number, for supporting older extension versions' objects + */ +enum pageinspect_version +{ + PAGEINSPECT_V1_8, + PAGEINSPECT_V1_9, +}; + +/* in rawpage.c */ +extern Page get_page_from_raw(bytea *raw_page); + +#endif /* _PAGEINSPECT_H_ */ diff --git a/contrib/pageinspect/rawpage.c b/contrib/pageinspect/rawpage.c new file mode 100644 index 0000000..c882a62 --- /dev/null +++ b/contrib/pageinspect/rawpage.c @@ -0,0 +1,371 @@ +/*------------------------------------------------------------------------- + * + * rawpage.c + * Functions to extract a raw page as bytea and inspect it + * + * Access-method specific inspection functions are in separate files. + * + * Copyright (c) 2007-2021, PostgreSQL Global Development Group + * + * IDENTIFICATION + * contrib/pageinspect/rawpage.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "access/htup_details.h" +#include "access/relation.h" +#include "catalog/namespace.h" +#include "catalog/pg_type.h" +#include "funcapi.h" +#include "miscadmin.h" +#include "pageinspect.h" +#include "storage/bufmgr.h" +#include "storage/checksum.h" +#include "utils/builtins.h" +#include "utils/pg_lsn.h" +#include "utils/rel.h" +#include "utils/varlena.h" + +PG_MODULE_MAGIC; + +static bytea *get_raw_page_internal(text *relname, ForkNumber forknum, + BlockNumber blkno); + + +/* + * get_raw_page + * + * Returns a copy of a page from shared buffers as a bytea + */ +PG_FUNCTION_INFO_V1(get_raw_page_1_9); + +Datum +get_raw_page_1_9(PG_FUNCTION_ARGS) +{ + text *relname = PG_GETARG_TEXT_PP(0); + int64 blkno = PG_GETARG_INT64(1); + bytea *raw_page; + + if (blkno < 0 || blkno > MaxBlockNumber) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid block number"))); + + raw_page = get_raw_page_internal(relname, MAIN_FORKNUM, blkno); + + PG_RETURN_BYTEA_P(raw_page); +} + +/* + * entry point for old extension version + */ +PG_FUNCTION_INFO_V1(get_raw_page); + +Datum +get_raw_page(PG_FUNCTION_ARGS) +{ + text *relname = PG_GETARG_TEXT_PP(0); + uint32 blkno = PG_GETARG_UINT32(1); + bytea *raw_page; + + /* + * We don't normally bother to check the number of arguments to a C + * function, but here it's needed for safety because early 8.4 beta + * releases mistakenly redefined get_raw_page() as taking three arguments. + */ + if (PG_NARGS() != 2) + ereport(ERROR, + (errmsg("wrong number of arguments to get_raw_page()"), + errhint("Run the updated pageinspect.sql script."))); + + raw_page = get_raw_page_internal(relname, MAIN_FORKNUM, blkno); + + PG_RETURN_BYTEA_P(raw_page); +} + +/* + * get_raw_page_fork + * + * Same, for any fork + */ +PG_FUNCTION_INFO_V1(get_raw_page_fork_1_9); + +Datum +get_raw_page_fork_1_9(PG_FUNCTION_ARGS) +{ + text *relname = PG_GETARG_TEXT_PP(0); + text *forkname = PG_GETARG_TEXT_PP(1); + int64 blkno = PG_GETARG_INT64(2); + bytea *raw_page; + ForkNumber forknum; + + forknum = forkname_to_number(text_to_cstring(forkname)); + + if (blkno < 0 || blkno > MaxBlockNumber) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid block number"))); + + raw_page = get_raw_page_internal(relname, forknum, blkno); + + PG_RETURN_BYTEA_P(raw_page); +} + +/* + * Entry point for old extension version + */ +PG_FUNCTION_INFO_V1(get_raw_page_fork); + +Datum +get_raw_page_fork(PG_FUNCTION_ARGS) +{ + text *relname = PG_GETARG_TEXT_PP(0); + text *forkname = PG_GETARG_TEXT_PP(1); + uint32 blkno = PG_GETARG_UINT32(2); + bytea *raw_page; + ForkNumber forknum; + + forknum = forkname_to_number(text_to_cstring(forkname)); + + raw_page = get_raw_page_internal(relname, forknum, blkno); + + PG_RETURN_BYTEA_P(raw_page); +} + +/* + * workhorse + */ +static bytea * +get_raw_page_internal(text *relname, ForkNumber forknum, BlockNumber blkno) +{ + bytea *raw_page; + RangeVar *relrv; + Relation rel; + char *raw_page_data; + Buffer buf; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); + rel = relation_openrv(relrv, AccessShareLock); + + /* Check that this relation has storage */ + if (rel->rd_rel->relkind == RELKIND_VIEW) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("cannot get raw page from view \"%s\"", + RelationGetRelationName(rel)))); + if (rel->rd_rel->relkind == RELKIND_COMPOSITE_TYPE) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("cannot get raw page from composite type \"%s\"", + RelationGetRelationName(rel)))); + if (rel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("cannot get raw page from foreign table \"%s\"", + RelationGetRelationName(rel)))); + if (rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("cannot get raw page from partitioned table \"%s\"", + RelationGetRelationName(rel)))); + if (rel->rd_rel->relkind == RELKIND_PARTITIONED_INDEX) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("cannot get raw page from partitioned index \"%s\"", + RelationGetRelationName(rel)))); + + /* + * Reject attempts to read non-local temporary relations; we would be + * likely to get wrong data since we have no visibility into the owning + * session's local buffers. + */ + if (RELATION_IS_OTHER_TEMP(rel)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot access temporary tables of other sessions"))); + + if (blkno >= RelationGetNumberOfBlocksInFork(rel, forknum)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("block number %u is out of range for relation \"%s\"", + blkno, RelationGetRelationName(rel)))); + + /* Initialize buffer to copy to */ + raw_page = (bytea *) palloc(BLCKSZ + VARHDRSZ); + SET_VARSIZE(raw_page, BLCKSZ + VARHDRSZ); + raw_page_data = VARDATA(raw_page); + + /* Take a verbatim copy of the page */ + + buf = ReadBufferExtended(rel, forknum, blkno, RBM_NORMAL, NULL); + LockBuffer(buf, BUFFER_LOCK_SHARE); + + memcpy(raw_page_data, BufferGetPage(buf), BLCKSZ); + + LockBuffer(buf, BUFFER_LOCK_UNLOCK); + ReleaseBuffer(buf); + + relation_close(rel, AccessShareLock); + + return raw_page; +} + + +/* + * get_page_from_raw + * + * Get a palloc'd, maxalign'ed page image from the result of get_raw_page() + * + * On machines with MAXALIGN = 8, the payload of a bytea is not maxaligned, + * since it will start 4 bytes into a palloc'd value. On alignment-picky + * machines, this will cause failures in accesses to 8-byte-wide values + * within the page. We don't need to worry if accessing only 4-byte or + * smaller fields, but when examining a struct that contains 8-byte fields, + * use this function for safety. + */ +Page +get_page_from_raw(bytea *raw_page) +{ + Page page; + int raw_page_size; + + raw_page_size = VARSIZE_ANY_EXHDR(raw_page); + + if (raw_page_size != BLCKSZ) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid page size"), + errdetail("Expected %d bytes, got %d.", + BLCKSZ, raw_page_size))); + + page = palloc(raw_page_size); + + memcpy(page, VARDATA_ANY(raw_page), raw_page_size); + + return page; +} + + +/* + * page_header + * + * Allows inspection of page header fields of a raw page + */ + +PG_FUNCTION_INFO_V1(page_header); + +Datum +page_header(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + + TupleDesc tupdesc; + + Datum result; + HeapTuple tuple; + Datum values[9]; + bool nulls[9]; + + PageHeader page; + XLogRecPtr lsn; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + page = (PageHeader) get_page_from_raw(raw_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"); + + /* Extract information from the page header */ + + lsn = PageGetLSN(page); + + /* pageinspect >= 1.2 uses pg_lsn instead of text for the LSN field. */ + if (TupleDescAttr(tupdesc, 0)->atttypid == TEXTOID) + { + char lsnchar[64]; + + snprintf(lsnchar, sizeof(lsnchar), "%X/%X", LSN_FORMAT_ARGS(lsn)); + values[0] = CStringGetTextDatum(lsnchar); + } + else + values[0] = LSNGetDatum(lsn); + values[1] = UInt16GetDatum(page->pd_checksum); + values[2] = UInt16GetDatum(page->pd_flags); + values[3] = UInt16GetDatum(page->pd_lower); + values[4] = UInt16GetDatum(page->pd_upper); + values[5] = UInt16GetDatum(page->pd_special); + values[6] = UInt16GetDatum(PageGetPageSize(page)); + values[7] = UInt16GetDatum(PageGetPageLayoutVersion(page)); + values[8] = TransactionIdGetDatum(page->pd_prune_xid); + + /* Build and return the tuple. */ + + memset(nulls, 0, sizeof(nulls)); + + tuple = heap_form_tuple(tupdesc, values, nulls); + result = HeapTupleGetDatum(tuple); + + PG_RETURN_DATUM(result); +} + +/* + * page_checksum + * + * Compute checksum of a raw page + */ + +PG_FUNCTION_INFO_V1(page_checksum_1_9); +PG_FUNCTION_INFO_V1(page_checksum); + +static Datum +page_checksum_internal(PG_FUNCTION_ARGS, enum pageinspect_version ext_version) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + int64 blkno = (ext_version == PAGEINSPECT_V1_8 ? PG_GETARG_UINT32(1) : PG_GETARG_INT64(1)); + Page page; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to use raw page functions"))); + + if (blkno < 0 || blkno > MaxBlockNumber) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid block number"))); + + page = get_page_from_raw(raw_page); + + if (PageIsNew(page)) + PG_RETURN_NULL(); + + PG_RETURN_INT16(pg_checksum_page((char *) page, blkno)); +} + +Datum +page_checksum_1_9(PG_FUNCTION_ARGS) +{ + return page_checksum_internal(fcinfo, PAGEINSPECT_V1_9); +} + +/* + * Entry point for old extension version + */ +Datum +page_checksum(PG_FUNCTION_ARGS) +{ + return page_checksum_internal(fcinfo, PAGEINSPECT_V1_8); +} diff --git a/contrib/pageinspect/sql/brin.sql b/contrib/pageinspect/sql/brin.sql new file mode 100644 index 0000000..45098c1 --- /dev/null +++ b/contrib/pageinspect/sql/brin.sql @@ -0,0 +1,37 @@ +CREATE TABLE test1 (a int, b text); +INSERT INTO test1 VALUES (1, 'one'); +CREATE INDEX test1_a_idx ON test1 USING brin (a); + +SELECT brin_page_type(get_raw_page('test1_a_idx', 0)); +SELECT brin_page_type(get_raw_page('test1_a_idx', 1)); +SELECT brin_page_type(get_raw_page('test1_a_idx', 2)); + +SELECT * FROM brin_metapage_info(get_raw_page('test1_a_idx', 0)); +SELECT * FROM brin_metapage_info(get_raw_page('test1_a_idx', 1)); + +SELECT * FROM brin_revmap_data(get_raw_page('test1_a_idx', 0)) LIMIT 5; +SELECT * FROM brin_revmap_data(get_raw_page('test1_a_idx', 1)) LIMIT 5; + +SELECT * FROM brin_page_items(get_raw_page('test1_a_idx', 2), 'test1_a_idx') + ORDER BY blknum, attnum LIMIT 5; + +-- Failure for non-BRIN index. +CREATE INDEX test1_a_btree ON test1 (a); +SELECT brin_page_items(get_raw_page('test1_a_btree', 0), 'test1_a_btree'); + +-- Mask DETAIL messages as these are not portable across architectures. +\set VERBOSITY terse +-- Invalid special area size +SELECT brin_page_type(get_raw_page('test1', 0)); +SELECT * FROM brin_metapage_info(get_raw_page('test1', 0)); +SELECT * FROM brin_revmap_data(get_raw_page('test1', 0)); +\set VERBOSITY default + +-- Tests with all-zero pages. +SHOW block_size \gset +SELECT brin_page_type(decode(repeat('00', :block_size), 'hex')); +SELECT brin_page_items(decode(repeat('00', :block_size), 'hex'), 'test1_a_idx'); +SELECT brin_metapage_info(decode(repeat('00', :block_size), 'hex')); +SELECT brin_revmap_data(decode(repeat('00', :block_size), 'hex')); + +DROP TABLE test1; diff --git a/contrib/pageinspect/sql/btree.sql b/contrib/pageinspect/sql/btree.sql new file mode 100644 index 0000000..1f554f0 --- /dev/null +++ b/contrib/pageinspect/sql/btree.sql @@ -0,0 +1,51 @@ +CREATE TABLE test1 (a int8, b int4range); +INSERT INTO test1 VALUES (72057594037927937, '[0,1)'); +CREATE INDEX test1_a_idx ON test1 USING btree (a); + +\x + +SELECT * FROM bt_metap('test1_a_idx'); + +SELECT * FROM bt_page_stats('test1_a_idx', -1); +SELECT * FROM bt_page_stats('test1_a_idx', 0); +SELECT * FROM bt_page_stats('test1_a_idx', 1); +SELECT * FROM bt_page_stats('test1_a_idx', 2); + +SELECT * FROM bt_page_items('test1_a_idx', -1); +SELECT * FROM bt_page_items('test1_a_idx', 0); +SELECT * FROM bt_page_items('test1_a_idx', 1); +SELECT * FROM bt_page_items('test1_a_idx', 2); + +SELECT * FROM bt_page_items(get_raw_page('test1_a_idx', -1)); +SELECT * FROM bt_page_items(get_raw_page('test1_a_idx', 0)); +SELECT * FROM bt_page_items(get_raw_page('test1_a_idx', 1)); +SELECT * FROM bt_page_items(get_raw_page('test1_a_idx', 2)); + +-- Failure when using a non-btree index. +CREATE INDEX test1_a_hash ON test1 USING hash(a); +SELECT bt_metap('test1_a_hash'); +SELECT bt_page_stats('test1_a_hash', 0); +SELECT bt_page_items('test1_a_hash', 0); +SELECT bt_page_items(get_raw_page('test1_a_hash', 0)); +CREATE INDEX test1_b_gist ON test1 USING gist(b); +-- Special area of GiST is the same as btree, this complains about inconsistent +-- leaf data on the page. +SELECT bt_page_items(get_raw_page('test1_b_gist', 0)); + +-- Several failure modes. +-- Suppress the DETAIL message, to allow the tests to work across various +-- page sizes and architectures. +\set VERBOSITY terse +-- invalid page size +SELECT bt_page_items('aaa'::bytea); +-- invalid special area size +CREATE INDEX test1_a_brin ON test1 USING brin(a); +SELECT bt_page_items(get_raw_page('test1', 0)); +SELECT bt_page_items(get_raw_page('test1_a_brin', 0)); +\set VERBOSITY default + +-- Tests with all-zero pages. +SHOW block_size \gset +SELECT bt_page_items(decode(repeat('00', :block_size), 'hex')); + +DROP TABLE test1; diff --git a/contrib/pageinspect/sql/checksum.sql b/contrib/pageinspect/sql/checksum.sql new file mode 100644 index 0000000..b877db0 --- /dev/null +++ b/contrib/pageinspect/sql/checksum.sql @@ -0,0 +1,31 @@ +-- +-- Verify correct calculation of checksums +-- +-- Postgres' checksum algorithm produces different answers on little-endian +-- and big-endian machines. The results of this test also vary depending +-- on the configured block size. This test has several different expected +-- results files to handle the following possibilities: +-- +-- BLCKSZ end file +-- 8K LE checksum.out +-- 8K BE checksum_1.out +-- +-- In future we might provide additional expected-results files for other +-- block sizes, but there seems little point as long as so many other +-- test scripts also show false failures for non-default block sizes. +-- + +-- This is to label the results files with blocksize: +SHOW block_size; + +SHOW block_size \gset + +-- Apply page_checksum() to some different data patterns and block numbers +SELECT blkno, + page_checksum(decode(repeat('01', :block_size), 'hex'), blkno) AS checksum_01, + page_checksum(decode(repeat('04', :block_size), 'hex'), blkno) AS checksum_04, + page_checksum(decode(repeat('ff', :block_size), 'hex'), blkno) AS checksum_ff, + page_checksum(decode(repeat('abcd', :block_size / 2), 'hex'), blkno) AS checksum_abcd, + page_checksum(decode(repeat('e6d6', :block_size / 2), 'hex'), blkno) AS checksum_e6d6, + page_checksum(decode(repeat('4a5e', :block_size / 2), 'hex'), blkno) AS checksum_4a5e + FROM generate_series(0, 100, 50) AS a (blkno); diff --git a/contrib/pageinspect/sql/gin.sql b/contrib/pageinspect/sql/gin.sql new file mode 100644 index 0000000..b57466d --- /dev/null +++ b/contrib/pageinspect/sql/gin.sql @@ -0,0 +1,41 @@ +CREATE TABLE test1 (x int, y int[]); +INSERT INTO test1 VALUES (1, ARRAY[11, 111]); +CREATE INDEX test1_y_idx ON test1 USING gin (y) WITH (fastupdate = off); + +\x + +SELECT * FROM gin_metapage_info(get_raw_page('test1_y_idx', 0)); +SELECT * FROM gin_metapage_info(get_raw_page('test1_y_idx', 1)); + +SELECT * FROM gin_page_opaque_info(get_raw_page('test1_y_idx', 1)); + +SELECT * FROM gin_leafpage_items(get_raw_page('test1_y_idx', 1)); + +INSERT INTO test1 SELECT x, ARRAY[1,10] FROM generate_series(2,10000) x; + +SELECT COUNT(*) > 0 +FROM gin_leafpage_items(get_raw_page('test1_y_idx', + (pg_relation_size('test1_y_idx') / + current_setting('block_size')::bigint)::int - 1)); + +-- Failure with various modes. +-- Suppress the DETAIL message, to allow the tests to work across various +-- page sizes and architectures. +\set VERBOSITY terse +-- invalid page size +SELECT gin_leafpage_items('aaa'::bytea); +SELECT gin_metapage_info('bbb'::bytea); +SELECT gin_page_opaque_info('ccc'::bytea); +-- invalid special area size +SELECT * FROM gin_metapage_info(get_raw_page('test1', 0)); +SELECT * FROM gin_page_opaque_info(get_raw_page('test1', 0)); +SELECT * FROM gin_leafpage_items(get_raw_page('test1', 0)); +\set VERBOSITY default + +-- Tests with all-zero pages. +SHOW block_size \gset +SELECT gin_leafpage_items(decode(repeat('00', :block_size), 'hex')); +SELECT gin_metapage_info(decode(repeat('00', :block_size), 'hex')); +SELECT gin_page_opaque_info(decode(repeat('00', :block_size), 'hex')); + +DROP TABLE test1; diff --git a/contrib/pageinspect/sql/gist.sql b/contrib/pageinspect/sql/gist.sql new file mode 100644 index 0000000..ee46e09 --- /dev/null +++ b/contrib/pageinspect/sql/gist.sql @@ -0,0 +1,53 @@ +-- The gist_page_opaque_info() function prints the page's LSN. Normally, +-- that's constant 1 (GistBuildLSN) on every page of a freshly built GiST +-- index. But with wal_level=minimal, the whole relation is dumped to WAL at +-- the end of the transaction if it's smaller than wal_skip_threshold, which +-- updates the LSNs. Wrap the tests on gist_page_opaque_info() in the +-- same transaction with the CREATE INDEX so that we see the LSNs before +-- they are possibly overwritten at end of transaction. +BEGIN; + +-- Create a test table and GiST index. +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); + +-- Page 0 is the root, the rest are leaf pages +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)); + +COMMIT; + +SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 0), 'test_gist_idx'); +SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 1), 'test_gist_idx') LIMIT 5; + +-- gist_page_items_bytea prints the raw key data as a bytea. The output of that is +-- platform-dependent (endianess), so omit the actual key data from the output. +SELECT itemoffset, ctid, itemlen FROM gist_page_items_bytea(get_raw_page('test_gist_idx', 0)); + +-- Failure with non-GiST index. +CREATE INDEX test_gist_btree on test_gist(t); +SELECT gist_page_items(get_raw_page('test_gist_btree', 0), 'test_gist_btree'); + +-- Failure with various modes. +-- Suppress the DETAIL message, to allow the tests to work across various +-- page sizes and architectures. +\set VERBOSITY terse +-- invalid page size +SELECT gist_page_items_bytea('aaa'::bytea); +SELECT gist_page_items('aaa'::bytea, 'test_gist_idx'::regclass); +SELECT gist_page_opaque_info('aaa'::bytea); +-- invalid special area size +SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist', 0)); +SELECT gist_page_items_bytea(get_raw_page('test_gist', 0)); +SELECT gist_page_items_bytea(get_raw_page('test_gist_btree', 0)); +\set VERBOSITY default + +-- Tests with all-zero pages. +SHOW block_size \gset +SELECT gist_page_items_bytea(decode(repeat('00', :block_size), 'hex')); +SELECT gist_page_items(decode(repeat('00', :block_size), 'hex'), 'test_gist_idx'::regclass); +SELECT gist_page_opaque_info(decode(repeat('00', :block_size), 'hex')); + +DROP TABLE test_gist; diff --git a/contrib/pageinspect/sql/hash.sql b/contrib/pageinspect/sql/hash.sql new file mode 100644 index 0000000..320fb9f --- /dev/null +++ b/contrib/pageinspect/sql/hash.sql @@ -0,0 +1,108 @@ +CREATE TABLE test_hash (a int, b text); +INSERT INTO test_hash VALUES (1, 'one'); +CREATE INDEX test_hash_a_idx ON test_hash USING hash (a); + +\x + +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 0)); +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 1)); +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 2)); +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 3)); +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 4)); +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 5)); +SELECT hash_page_type(get_raw_page('test_hash_a_idx', 6)); + + +SELECT * FROM hash_bitmap_info('test_hash_a_idx', -1); +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 0); +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 1); +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 2); +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 3); +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 4); +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 5); +SELECT * FROM hash_bitmap_info('test_hash_a_idx', 6); + + +SELECT magic, version, ntuples, bsize, bmsize, bmshift, maxbucket, highmask, +lowmask, ovflpoint, firstfree, nmaps, procid, spares, mapp FROM +hash_metapage_info(get_raw_page('test_hash_a_idx', 0)); + +SELECT magic, version, ntuples, bsize, bmsize, bmshift, maxbucket, highmask, +lowmask, ovflpoint, firstfree, nmaps, procid, spares, mapp FROM +hash_metapage_info(get_raw_page('test_hash_a_idx', 1)); + +SELECT magic, version, ntuples, bsize, bmsize, bmshift, maxbucket, highmask, +lowmask, ovflpoint, firstfree, nmaps, procid, spares, mapp FROM +hash_metapage_info(get_raw_page('test_hash_a_idx', 2)); + +SELECT magic, version, ntuples, bsize, bmsize, bmshift, maxbucket, highmask, +lowmask, ovflpoint, firstfree, nmaps, procid, spares, mapp FROM +hash_metapage_info(get_raw_page('test_hash_a_idx', 3)); + +SELECT magic, version, ntuples, bsize, bmsize, bmshift, maxbucket, highmask, +lowmask, ovflpoint, firstfree, nmaps, procid, spares, mapp FROM +hash_metapage_info(get_raw_page('test_hash_a_idx', 4)); + +SELECT magic, version, ntuples, bsize, bmsize, bmshift, maxbucket, highmask, +lowmask, ovflpoint, firstfree, nmaps, procid, spares, mapp FROM +hash_metapage_info(get_raw_page('test_hash_a_idx', 5)); + +SELECT live_items, dead_items, page_size, hasho_prevblkno, hasho_nextblkno, +hasho_bucket, hasho_flag, hasho_page_id FROM +hash_page_stats(get_raw_page('test_hash_a_idx', 0)); + +SELECT live_items, dead_items, page_size, hasho_prevblkno, hasho_nextblkno, +hasho_bucket, hasho_flag, hasho_page_id FROM +hash_page_stats(get_raw_page('test_hash_a_idx', 1)); + +SELECT live_items, dead_items, page_size, hasho_prevblkno, hasho_nextblkno, +hasho_bucket, hasho_flag, hasho_page_id FROM +hash_page_stats(get_raw_page('test_hash_a_idx', 2)); + +SELECT live_items, dead_items, page_size, hasho_prevblkno, hasho_nextblkno, +hasho_bucket, hasho_flag, hasho_page_id FROM +hash_page_stats(get_raw_page('test_hash_a_idx', 3)); + +SELECT live_items, dead_items, page_size, hasho_prevblkno, hasho_nextblkno, +hasho_bucket, hasho_flag, hasho_page_id FROM +hash_page_stats(get_raw_page('test_hash_a_idx', 4)); + +SELECT live_items, dead_items, page_size, hasho_prevblkno, hasho_nextblkno, +hasho_bucket, hasho_flag, hasho_page_id FROM +hash_page_stats(get_raw_page('test_hash_a_idx', 5)); + +SELECT * FROM hash_page_items(get_raw_page('test_hash_a_idx', 0)); +SELECT * FROM hash_page_items(get_raw_page('test_hash_a_idx', 1)); +SELECT * FROM hash_page_items(get_raw_page('test_hash_a_idx', 2)); +SELECT * FROM hash_page_items(get_raw_page('test_hash_a_idx', 3)); +SELECT * FROM hash_page_items(get_raw_page('test_hash_a_idx', 4)); +SELECT * FROM hash_page_items(get_raw_page('test_hash_a_idx', 5)); + +-- Failure with non-hash index +CREATE INDEX test_hash_a_btree ON test_hash USING btree (a); +SELECT hash_bitmap_info('test_hash_a_btree', 0); + +-- Failure with various modes. +-- Suppress the DETAIL message, to allow the tests to work across various +-- page sizes and architectures. +\set VERBOSITY terse +-- invalid page size +SELECT hash_metapage_info('aaa'::bytea); +SELECT hash_page_items('bbb'::bytea); +SELECT hash_page_stats('ccc'::bytea); +SELECT hash_page_type('ddd'::bytea); +-- invalid special area size +SELECT hash_metapage_info(get_raw_page('test_hash', 0)); +SELECT hash_page_items(get_raw_page('test_hash', 0)); +SELECT hash_page_stats(get_raw_page('test_hash', 0)); +SELECT hash_page_type(get_raw_page('test_hash', 0)); +\set VERBOSITY default + +-- Tests with all-zero pages. +SHOW block_size \gset +SELECT hash_metapage_info(decode(repeat('00', :block_size), 'hex')); +SELECT hash_page_items(decode(repeat('00', :block_size), 'hex')); +SELECT hash_page_stats(decode(repeat('00', :block_size), 'hex')); +SELECT hash_page_type(decode(repeat('00', :block_size), 'hex')); + +DROP TABLE test_hash; diff --git a/contrib/pageinspect/sql/oldextversions.sql b/contrib/pageinspect/sql/oldextversions.sql new file mode 100644 index 0000000..78e08f4 --- /dev/null +++ b/contrib/pageinspect/sql/oldextversions.sql @@ -0,0 +1,20 @@ +-- test old extension version entry points + +DROP EXTENSION pageinspect; +CREATE EXTENSION pageinspect VERSION '1.8'; + +CREATE TABLE test1 (a int8, b text); +INSERT INTO test1 VALUES (72057594037927937, 'text'); +CREATE INDEX test1_a_idx ON test1 USING btree (a); + +-- from page.sql +SELECT octet_length(get_raw_page('test1', 0)) AS main_0; +SELECT octet_length(get_raw_page('test1', 'main', 0)) AS main_0; +SELECT page_checksum(get_raw_page('test1', 0), 0) IS NOT NULL AS silly_checksum_test; + +-- from btree.sql +SELECT * FROM bt_page_stats('test1_a_idx', 1); +SELECT * FROM bt_page_items('test1_a_idx', 1); + +DROP TABLE test1; +DROP EXTENSION pageinspect; diff --git a/contrib/pageinspect/sql/page.sql b/contrib/pageinspect/sql/page.sql new file mode 100644 index 0000000..b5c41cc --- /dev/null +++ b/contrib/pageinspect/sql/page.sql @@ -0,0 +1,99 @@ +CREATE EXTENSION pageinspect; + +CREATE TABLE test1 (a int, b int); +INSERT INTO test1 VALUES (16777217, 131584); + +VACUUM (DISABLE_PAGE_SKIPPING) test1; -- set up FSM + +-- The page contents can vary, so just test that it can be read +-- successfully, but don't keep the output. + +SELECT octet_length(get_raw_page('test1', 'main', 0)) AS main_0; +SELECT octet_length(get_raw_page('test1', 'main', 1)) AS main_1; + +SELECT octet_length(get_raw_page('test1', 'fsm', 0)) AS fsm_0; +SELECT octet_length(get_raw_page('test1', 'fsm', 1)) AS fsm_1; + +SELECT octet_length(get_raw_page('test1', 'vm', 0)) AS vm_0; +SELECT octet_length(get_raw_page('test1', 'vm', 1)) AS vm_1; + +SELECT octet_length(get_raw_page('test1', 'main', -1)); +SELECT octet_length(get_raw_page('xxx', 'main', 0)); +SELECT octet_length(get_raw_page('test1', 'xxx', 0)); + +SELECT get_raw_page('test1', 0) = get_raw_page('test1', 'main', 0); + +SELECT pagesize, version FROM page_header(get_raw_page('test1', 0)); + +SELECT page_checksum(get_raw_page('test1', 0), 0) IS NOT NULL AS silly_checksum_test; +SELECT page_checksum(get_raw_page('test1', 0), -1); + +SELECT tuple_data_split('test1'::regclass, t_data, t_infomask, t_infomask2, t_bits) + FROM heap_page_items(get_raw_page('test1', 0)); + +SELECT * FROM fsm_page_contents(get_raw_page('test1', 'fsm', 0)); + +-- If we freeze the only tuple on test1, the infomask should +-- always be the same in all test runs. +VACUUM (FREEZE, DISABLE_PAGE_SKIPPING) test1; + +SELECT t_infomask, t_infomask2, raw_flags, combined_flags +FROM heap_page_items(get_raw_page('test1', 0)), + LATERAL heap_tuple_infomask_flags(t_infomask, t_infomask2); + +-- tests for decoding of combined flags +-- HEAP_XMAX_SHR_LOCK = (HEAP_XMAX_EXCL_LOCK | HEAP_XMAX_KEYSHR_LOCK) +SELECT * FROM heap_tuple_infomask_flags(x'0050'::int, 0); +-- HEAP_XMIN_FROZEN = (HEAP_XMIN_COMMITTED | HEAP_XMIN_INVALID) +SELECT * FROM heap_tuple_infomask_flags(x'0300'::int, 0); +-- HEAP_MOVED = (HEAP_MOVED_IN | HEAP_MOVED_OFF) +SELECT * FROM heap_tuple_infomask_flags(x'C000'::int, 0); +SELECT * FROM heap_tuple_infomask_flags(x'C000'::int, 0); + +-- test all flags of t_infomask and t_infomask2 +SELECT unnest(raw_flags) + FROM heap_tuple_infomask_flags(x'FFFF'::int, x'FFFF'::int) ORDER BY 1; +SELECT unnest(combined_flags) + FROM heap_tuple_infomask_flags(x'FFFF'::int, x'FFFF'::int) ORDER BY 1; + +-- no flags at all +SELECT * FROM heap_tuple_infomask_flags(0, 0); +-- no combined flags +SELECT * FROM heap_tuple_infomask_flags(x'0010'::int, 0); + +DROP TABLE test1; + +-- check that using any of these functions with a partitioned table or index +-- would fail +create table test_partitioned (a int) partition by range (a); +create index test_partitioned_index on test_partitioned (a); +select get_raw_page('test_partitioned', 0); -- error about partitioned table +select get_raw_page('test_partitioned_index', 0); -- error about partitioned index + +-- a regular table which is a member of a partition set should work though +create table test_part1 partition of test_partitioned for values from ( 1 ) to (100); +select get_raw_page('test_part1', 0); -- get farther and error about empty table +drop table test_partitioned; + +-- check null bitmap alignment for table whose number of attributes is multiple of 8 +create table test8 (f1 int, f2 int, f3 int, f4 int, f5 int, f6 int, f7 int, f8 int); +insert into test8(f1, f8) values (x'7f00007f'::int, 0); +select t_bits, t_data from heap_page_items(get_raw_page('test8', 0)); +select tuple_data_split('test8'::regclass, t_data, t_infomask, t_infomask2, t_bits) + from heap_page_items(get_raw_page('test8', 0)); +drop table test8; + +-- Failure with incorrect page size +-- Suppress the DETAIL message, to allow the tests to work across various +-- page sizes. +\set VERBOSITY terse +SELECT fsm_page_contents('aaa'::bytea); +SELECT page_checksum('bbb'::bytea, 0); +SELECT page_header('ccc'::bytea); +\set VERBOSITY default + +-- Tests with all-zero pages. +SHOW block_size \gset +SELECT fsm_page_contents(decode(repeat('00', :block_size), 'hex')); +SELECT page_header(decode(repeat('00', :block_size), 'hex')); +SELECT page_checksum(decode(repeat('00', :block_size), 'hex'), 1); |