diff --git a/contrib/pg_upgrade/info.c b/contrib/pg_upgrade/info.c index c381f11..18daf1c 100644 --- a/contrib/pg_upgrade/info.c +++ b/contrib/pg_upgrade/info.c @@ -321,12 +321,19 @@ get_rel_infos(ClusterInfo *cluster, DbInfo *dbinfo) "INSERT INTO info_rels " "SELECT reltoastrelid " "FROM info_rels i JOIN pg_catalog.pg_class c " - " ON i.reloid = c.oid")); + " ON i.reloid = c.oid " + " AND c.reltoastrelid != %u", InvalidOid)); PQclear(executeQueryOrDie(conn, "INSERT INTO info_rels " - "SELECT reltoastidxid " - "FROM info_rels i JOIN pg_catalog.pg_class c " - " ON i.reloid = c.oid")); + "SELECT indexrelid " + "FROM pg_index " + "WHERE indisvalid " + " AND indrelid IN (SELECT reltoastrelid " + " FROM info_rels i " + " JOIN pg_catalog.pg_class c " + " ON i.reloid = c.oid " + " AND c.reltoastrelid != %u)", + InvalidOid)); snprintf(query, sizeof(query), "SELECT c.oid, n.nspname, c.relname, " diff --git a/doc/src/sgml/catalogs.sgml b/doc/src/sgml/catalogs.sgml index e638a8f..f3d1d9e 100644 --- a/doc/src/sgml/catalogs.sgml +++ b/doc/src/sgml/catalogs.sgml @@ -1745,15 +1745,6 @@ - reltoastidxid - oid - pg_class.oid - - For a TOAST table, the OID of its index. 0 if not a TOAST table. - - - - relhasindex bool diff --git a/doc/src/sgml/diskusage.sgml b/doc/src/sgml/diskusage.sgml index de1d0b4..461deb9 100644 --- a/doc/src/sgml/diskusage.sgml +++ b/doc/src/sgml/diskusage.sgml @@ -20,12 +20,12 @@ stored. If the table has any columns with potentially-wide values, there also might be a TOAST file associated with the table, which is used to store values too wide to fit comfortably in the main - table (see ). There will be one index on the - TOAST table, if present. There also might be indexes associated - with the base table. Each table and index is stored in a separate disk - file — possibly more than one file, if the file would exceed one - gigabyte. Naming conventions for these files are described in . + table (see ). There will be one valid index + on the TOAST table, if present. There also might be indexes + associated with the base table. Each table and index is stored in a + separate disk file — possibly more than one file, if the file would + exceed one gigabyte. Naming conventions for these files are described + in . @@ -44,7 +44,7 @@ SELECT pg_relation_filepath(oid), relpages FROM pg_class WHERE relname = 'customer'; - pg_relation_filepath | relpages + pg_relation_filepath | relpages ----------------------+---------- base/16384/16806 | 60 (1 row) @@ -65,12 +65,12 @@ FROM pg_class, FROM pg_class WHERE relname = 'customer') AS ss WHERE oid = ss.reltoastrelid OR - oid = (SELECT reltoastidxid - FROM pg_class - WHERE oid = ss.reltoastrelid) + oid = (SELECT indexrelid + FROM pg_index + WHERE indrelid = ss.reltoastrelid) ORDER BY relname; - relname | relpages + relname | relpages ----------------------+---------- pg_toast_16806 | 0 pg_toast_16806_index | 1 @@ -87,7 +87,7 @@ WHERE c.relname = 'customer' AND c2.oid = i.indexrelid ORDER BY c2.relname; - relname | relpages + relname | relpages ----------------------+---------- customer_id_indexdex | 26 @@ -101,7 +101,7 @@ SELECT relname, relpages FROM pg_class ORDER BY relpages DESC; - relname | relpages + relname | relpages ----------------------+---------- bigtable | 3290 customer | 3144 diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index b37b6c3..d38c009 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -1163,12 +1163,12 @@ postgres: user database host tidx_blks_read bigint - Number of disk blocks read from this table's TOAST table index (if any) + Number of disk blocks read from this table's TOAST table indexes (if any) tidx_blks_hit bigint - Number of buffer hits in this table's TOAST table index (if any) + Number of buffer hits in this table's TOAST table indexes (if any) diff --git a/src/backend/access/heap/tuptoaster.c b/src/backend/access/heap/tuptoaster.c index fc37ceb..8457777 100644 --- a/src/backend/access/heap/tuptoaster.c +++ b/src/backend/access/heap/tuptoaster.c @@ -76,11 +76,13 @@ do { \ static void toast_delete_datum(Relation rel, Datum value); static Datum toast_save_datum(Relation rel, Datum value, struct varlena * oldexternal, int options); -static bool toastrel_valueid_exists(Relation toastrel, Oid valueid); +static bool toastrel_valueid_exists(Relation toastrel, + Oid valueid, LOCKMODE lockmode); static bool toastid_valueid_exists(Oid toastrelid, Oid valueid); static struct varlena *toast_fetch_datum(struct varlena * attr); static struct varlena *toast_fetch_datum_slice(struct varlena * attr, int32 sliceoffset, int32 length); +static Relation toast_index_fetch_valid(Relation *toastidxs, int num_indexes); /* ---------- @@ -1222,6 +1224,49 @@ toast_compress_datum(Datum value) /* ---------- + * toast_get_valid_index + * + * Get the valid index of given toast relation. A toast relation can only + * have one valid index at the same time. The lock taken on the index + * relations is released at the end of this function call. + */ +Oid +toast_get_valid_index(Oid toastoid, LOCKMODE lock) +{ + ListCell *lc; + List *indexlist; + int num_indexes, i = 0; + Oid validIndexOid; + Relation validIndexRel; + Relation *toastidxs; + Relation toastrel; + + /* Get the index list of relation */ + toastrel = heap_open(toastoid, lock); + indexlist = RelationGetIndexList(toastrel); + num_indexes = list_length(indexlist); + + /* Open all the index relations */ + toastidxs = (Relation *) palloc(num_indexes * sizeof(Relation)); + foreach(lc, indexlist) + toastidxs[i++] = index_open(lfirst_oid(lc), lock); + + /* Fetch valid toast index */ + validIndexRel = toast_index_fetch_valid(toastidxs, num_indexes); + validIndexOid = RelationGetRelid(validIndexRel); + + /* Close all the index relations */ + for (i = 0; i < num_indexes; i++) + index_close(toastidxs[i], lock); + pfree(toastidxs); + list_free(indexlist); + + heap_close(toastrel, lock); + return validIndexOid; +} + + +/* ---------- * toast_save_datum - * * Save one single datum into the secondary relation and return @@ -1237,8 +1282,8 @@ static Datum toast_save_datum(Relation rel, Datum value, struct varlena * oldexternal, int options) { - Relation toastrel; - Relation toastidx; + Relation toastrel, validtoastidx; + Relation *toastidxs; HeapTuple toasttup; TupleDesc toasttupDesc; Datum t_values[3]; @@ -1257,15 +1302,30 @@ toast_save_datum(Relation rel, Datum value, char *data_p; int32 data_todo; Pointer dval = DatumGetPointer(value); + ListCell *lc; + List *indexlist; + int i = 0; + int num_indexes; /* * Open the toast relation and its index. We can use the index to check * uniqueness of the OID we assign to the toasted item, even though it has - * additional columns besides OID. + * additional columns besides OID. A toast table can have multiple identical + * indexes associated to it. */ toastrel = heap_open(rel->rd_rel->reltoastrelid, RowExclusiveLock); toasttupDesc = toastrel->rd_att; - toastidx = index_open(toastrel->rd_rel->reltoastidxid, RowExclusiveLock); + indexlist = RelationGetIndexList(toastrel); + num_indexes = list_length(indexlist); + + toastidxs = (Relation *) palloc(num_indexes * sizeof(Relation)); + + /* Open all the indexes of toast relation with similar lock */ + foreach(lc, indexlist) + toastidxs[i++] = index_open(lfirst_oid(lc), RowExclusiveLock); + + /* Fetch relation used for process */ + validtoastidx = toast_index_fetch_valid(toastidxs, num_indexes); /* * Get the data pointer and length, and compute va_rawsize and va_extsize. @@ -1330,7 +1390,7 @@ toast_save_datum(Relation rel, Datum value, /* normal case: just choose an unused OID */ toast_pointer.va_valueid = GetNewOidWithIndex(toastrel, - RelationGetRelid(toastidx), + RelationGetRelid(validtoastidx), (AttrNumber) 1); } else @@ -1367,7 +1427,8 @@ toast_save_datum(Relation rel, Datum value, * be reclaimed by VACUUM. */ if (toastrel_valueid_exists(toastrel, - toast_pointer.va_valueid)) + toast_pointer.va_valueid, + RowExclusiveLock)) { /* Match, so short-circuit the data storage loop below */ data_todo = 0; @@ -1384,7 +1445,7 @@ toast_save_datum(Relation rel, Datum value, { toast_pointer.va_valueid = GetNewOidWithIndex(toastrel, - RelationGetRelid(toastidx), + RelationGetRelid(validtoastidx), (AttrNumber) 1); } while (toastid_valueid_exists(rel->rd_toastoid, toast_pointer.va_valueid)); @@ -1423,16 +1484,18 @@ toast_save_datum(Relation rel, Datum value, /* * Create the index entry. We cheat a little here by not using * FormIndexDatum: this relies on the knowledge that the index columns - * are the same as the initial columns of the table. + * are the same as the initial columns of the table for all the + * indexes. * * Note also that there had better not be any user-created index on * the TOAST table, since we don't bother to update anything else. */ - index_insert(toastidx, t_values, t_isnull, - &(toasttup->t_self), - toastrel, - toastidx->rd_index->indisunique ? - UNIQUE_CHECK_YES : UNIQUE_CHECK_NO); + for (i = 0; i < num_indexes; i++) + index_insert(toastidxs[i], t_values, t_isnull, + &(toasttup->t_self), + toastrel, + toastidxs[i]->rd_index->indisunique ? + UNIQUE_CHECK_YES : UNIQUE_CHECK_NO); /* * Free memory @@ -1447,10 +1510,13 @@ toast_save_datum(Relation rel, Datum value, } /* - * Done - close toast relation + * Done - close toast relations */ - index_close(toastidx, RowExclusiveLock); + for (i = 0; i < num_indexes; i++) + index_close(toastidxs[i], RowExclusiveLock); + list_free(indexlist); heap_close(toastrel, RowExclusiveLock); + pfree(toastidxs); /* * Create the TOAST pointer value that we'll return @@ -1474,11 +1540,15 @@ toast_delete_datum(Relation rel, Datum value) { struct varlena *attr = (struct varlena *) DatumGetPointer(value); struct varatt_external toast_pointer; - Relation toastrel; - Relation toastidx; + Relation toastrel, validtoastidx; + Relation *toastidxs; ScanKeyData toastkey; SysScanDesc toastscan; HeapTuple toasttup; + ListCell *lc; + List *indexlist; + int num_indexes; + int i = 0; if (!VARATT_IS_EXTERNAL(attr)) return; @@ -1487,10 +1557,22 @@ toast_delete_datum(Relation rel, Datum value) VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr); /* - * Open the toast relation and its index + * Open the toast relation and its indexes */ toastrel = heap_open(toast_pointer.va_toastrelid, RowExclusiveLock); - toastidx = index_open(toastrel->rd_rel->reltoastidxid, RowExclusiveLock); + indexlist = RelationGetIndexList(toastrel); + num_indexes = list_length(indexlist); + toastidxs = (Relation *) palloc(num_indexes * sizeof(Relation)); + + /* + * We actually use only the first valid index but taking a lock on all is + * necessary. + */ + foreach(lc, indexlist) + toastidxs[i++] = index_open(lfirst_oid(lc), RowExclusiveLock); + + /* Fetch relation used for process */ + validtoastidx = toast_index_fetch_valid(toastidxs, num_indexes); /* * Setup a scan key to find chunks with matching va_valueid @@ -1505,7 +1587,7 @@ toast_delete_datum(Relation rel, Datum value) * sequence or not, but since we've already locked the index we might as * well use systable_beginscan_ordered.) */ - toastscan = systable_beginscan_ordered(toastrel, toastidx, + toastscan = systable_beginscan_ordered(toastrel, validtoastidx, SnapshotToast, 1, &toastkey); while ((toasttup = systable_getnext_ordered(toastscan, ForwardScanDirection)) != NULL) { @@ -1519,8 +1601,11 @@ toast_delete_datum(Relation rel, Datum value) * End scan and close relations */ systable_endscan_ordered(toastscan); - index_close(toastidx, RowExclusiveLock); + for (i = 0; i < num_indexes; i++) + index_close(toastidxs[i], RowExclusiveLock); + list_free(indexlist); heap_close(toastrel, RowExclusiveLock); + pfree(toastidxs); } @@ -1531,11 +1616,29 @@ toast_delete_datum(Relation rel, Datum value) * ---------- */ static bool -toastrel_valueid_exists(Relation toastrel, Oid valueid) +toastrel_valueid_exists(Relation toastrel, Oid valueid, LOCKMODE lockmode) { bool result = false; ScanKeyData toastkey; SysScanDesc toastscan; + int i = 0; + int num_indexes; + Relation *toastidxs; + Relation validtoastidx; + ListCell *lc; + List *indexlist; + + /* Ensure that the list of indexes of toast relation is computed */ + indexlist = RelationGetIndexList(toastrel); + num_indexes = list_length(indexlist); + + /* Open each index relation necessary */ + toastidxs = (Relation *) palloc(num_indexes * sizeof(Relation)); + foreach(lc, indexlist) + toastidxs[i++] = index_open(lfirst_oid(lc), lockmode); + + /* Fetch a valid index relation */ + validtoastidx = toast_index_fetch_valid(toastidxs, num_indexes); /* * Setup a scan key to find chunks with matching va_valueid @@ -1548,7 +1651,8 @@ toastrel_valueid_exists(Relation toastrel, Oid valueid) /* * Is there any such chunk? */ - toastscan = systable_beginscan(toastrel, toastrel->rd_rel->reltoastidxid, + toastscan = systable_beginscan(toastrel, + RelationGetRelid(validtoastidx), true, SnapshotToast, 1, &toastkey); if (systable_getnext(toastscan) != NULL) @@ -1556,6 +1660,12 @@ toastrel_valueid_exists(Relation toastrel, Oid valueid) systable_endscan(toastscan); + /* Clean up */ + for (i = 0; i < num_indexes; i++) + index_close(toastidxs[i], lockmode); + list_free(indexlist); + pfree(toastidxs); + return result; } @@ -1573,7 +1683,7 @@ toastid_valueid_exists(Oid toastrelid, Oid valueid) toastrel = heap_open(toastrelid, AccessShareLock); - result = toastrel_valueid_exists(toastrel, valueid); + result = toastrel_valueid_exists(toastrel, valueid, AccessShareLock); heap_close(toastrel, AccessShareLock); @@ -1591,8 +1701,8 @@ toastid_valueid_exists(Oid toastrelid, Oid valueid) static struct varlena * toast_fetch_datum(struct varlena * attr) { - Relation toastrel; - Relation toastidx; + Relation toastrel, validtoastidx; + Relation *toastidxs; ScanKeyData toastkey; SysScanDesc toastscan; HeapTuple ttup; @@ -1607,6 +1717,10 @@ toast_fetch_datum(struct varlena * attr) bool isnull; char *chunkdata; int32 chunksize; + ListCell *lc; + List *indexlist; + int num_indexes; + int i = 0; /* Must copy to access aligned fields */ VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr); @@ -1622,11 +1736,21 @@ toast_fetch_datum(struct varlena * attr) SET_VARSIZE(result, ressize + VARHDRSZ); /* - * Open the toast relation and its index + * Open the toast relation and its indexes */ toastrel = heap_open(toast_pointer.va_toastrelid, AccessShareLock); toasttupDesc = toastrel->rd_att; - toastidx = index_open(toastrel->rd_rel->reltoastidxid, AccessShareLock); + indexlist = RelationGetIndexList(toastrel); + num_indexes = list_length(indexlist); + + toastidxs = (Relation *) palloc(num_indexes * sizeof(Relation)); + + /* Open all the indexes of toast relation with similar lock */ + foreach(lc, indexlist) + toastidxs[i++] = index_open(lfirst_oid(lc), AccessShareLock); + + /* Fetch relation used for process */ + validtoastidx = toast_index_fetch_valid(toastidxs, num_indexes); /* * Setup a scan key to fetch from the index by va_valueid @@ -1645,7 +1769,7 @@ toast_fetch_datum(struct varlena * attr) */ nextidx = 0; - toastscan = systable_beginscan_ordered(toastrel, toastidx, + toastscan = systable_beginscan_ordered(toastrel, validtoastidx, SnapshotToast, 1, &toastkey); while ((ttup = systable_getnext_ordered(toastscan, ForwardScanDirection)) != NULL) { @@ -1734,8 +1858,11 @@ toast_fetch_datum(struct varlena * attr) * End scan and close relations */ systable_endscan_ordered(toastscan); - index_close(toastidx, AccessShareLock); + for (i = 0; i < num_indexes; i++) + index_close(toastidxs[i], AccessShareLock); + list_free(indexlist); heap_close(toastrel, AccessShareLock); + pfree(toastidxs); return result; } @@ -1750,8 +1877,8 @@ toast_fetch_datum(struct varlena * attr) static struct varlena * toast_fetch_datum_slice(struct varlena * attr, int32 sliceoffset, int32 length) { - Relation toastrel; - Relation toastidx; + Relation toastrel, validtoastidx; + Relation *toastidxs; ScanKeyData toastkey[3]; int nscankeys; SysScanDesc toastscan; @@ -1774,6 +1901,10 @@ toast_fetch_datum_slice(struct varlena * attr, int32 sliceoffset, int32 length) int32 chunksize; int32 chcpystrt; int32 chcpyend; + int num_indexes; + int i = 0; + ListCell *lc; + List *indexlist; Assert(VARATT_IS_EXTERNAL(attr)); @@ -1816,11 +1947,18 @@ toast_fetch_datum_slice(struct varlena * attr, int32 sliceoffset, int32 length) endoffset = (sliceoffset + length - 1) % TOAST_MAX_CHUNK_SIZE; /* - * Open the toast relation and its index + * Open the toast relation and its indexes */ toastrel = heap_open(toast_pointer.va_toastrelid, AccessShareLock); toasttupDesc = toastrel->rd_att; - toastidx = index_open(toastrel->rd_rel->reltoastidxid, AccessShareLock); + indexlist = RelationGetIndexList(toastrel); + num_indexes = list_length(indexlist); + + toastidxs = (Relation *) palloc(num_indexes * sizeof(Relation)); + + foreach(lc, indexlist) + toastidxs[i++] = index_open(lfirst_oid(lc), AccessShareLock); + validtoastidx = toast_index_fetch_valid(toastidxs, num_indexes); /* * Setup a scan key to fetch from the index. This is either two keys or @@ -1861,7 +1999,7 @@ toast_fetch_datum_slice(struct varlena * attr, int32 sliceoffset, int32 length) * The index is on (valueid, chunkidx) so they will come in order */ nextidx = startchunk; - toastscan = systable_beginscan_ordered(toastrel, toastidx, + toastscan = systable_beginscan_ordered(toastrel, validtoastidx, SnapshotToast, nscankeys, toastkey); while ((ttup = systable_getnext_ordered(toastscan, ForwardScanDirection)) != NULL) { @@ -1958,8 +2096,37 @@ toast_fetch_datum_slice(struct varlena * attr, int32 sliceoffset, int32 length) * End scan and close relations */ systable_endscan_ordered(toastscan); - index_close(toastidx, AccessShareLock); + for (i = 0; i < num_indexes; i++) + index_close(toastidxs[i], AccessShareLock); + list_free(indexlist); heap_close(toastrel, AccessShareLock); + pfree(toastidxs); return result; } + +/* ---------- + * toast_index_fetch_valid + * + * Get a valid index in list of indexes for a toast relation. Those relations + * need to be already open prior calling this routine. + */ +static Relation +toast_index_fetch_valid(Relation *toastidxs, int num_indexes) +{ + int i; + Relation res = NULL; + + /* Fetch the first valid index in list */ + for (i = 0; i < num_indexes; i++) + { + if (toastidxs[i]->rd_index->indisvalid) + { + res = toastidxs[i]; + break; + } + } + + Assert(res); + return res; +} diff --git a/src/backend/catalog/heap.c b/src/backend/catalog/heap.c index 45a84e4..e08954e 100644 --- a/src/backend/catalog/heap.c +++ b/src/backend/catalog/heap.c @@ -781,7 +781,6 @@ InsertPgClassTuple(Relation pg_class_desc, values[Anum_pg_class_reltuples - 1] = Float4GetDatum(rd_rel->reltuples); values[Anum_pg_class_relallvisible - 1] = Int32GetDatum(rd_rel->relallvisible); values[Anum_pg_class_reltoastrelid - 1] = ObjectIdGetDatum(rd_rel->reltoastrelid); - values[Anum_pg_class_reltoastidxid - 1] = ObjectIdGetDatum(rd_rel->reltoastidxid); values[Anum_pg_class_relhasindex - 1] = BoolGetDatum(rd_rel->relhasindex); values[Anum_pg_class_relisshared - 1] = BoolGetDatum(rd_rel->relisshared); values[Anum_pg_class_relpersistence - 1] = CharGetDatum(rd_rel->relpersistence); diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c index 5f61ecb..e196a0c 100644 --- a/src/backend/catalog/index.c +++ b/src/backend/catalog/index.c @@ -103,7 +103,7 @@ static void UpdateIndexRelation(Oid indexoid, Oid heapoid, bool isvalid); static void index_update_stats(Relation rel, bool hasindex, bool isprimary, - Oid reltoastidxid, double reltuples); + double reltuples); static void IndexCheckExclusion(Relation heapRelation, Relation indexRelation, IndexInfo *indexInfo); @@ -1072,7 +1072,6 @@ index_create(Relation heapRelation, index_update_stats(heapRelation, true, isprimary, - InvalidOid, -1.0); /* Make the above update visible */ CommandCounterIncrement(); @@ -1254,7 +1253,6 @@ index_constraint_create(Relation heapRelation, index_update_stats(heapRelation, true, true, - InvalidOid, -1.0); /* @@ -1764,8 +1762,6 @@ FormIndexDatum(IndexInfo *indexInfo, * * hasindex: set relhasindex to this value * isprimary: if true, set relhaspkey true; else no change - * reltoastidxid: if not InvalidOid, set reltoastidxid to this value; - * else no change * reltuples: if >= 0, set reltuples to this value; else no change * * If reltuples >= 0, relpages and relallvisible are also updated (using @@ -1781,8 +1777,9 @@ FormIndexDatum(IndexInfo *indexInfo, */ static void index_update_stats(Relation rel, - bool hasindex, bool isprimary, - Oid reltoastidxid, double reltuples) + bool hasindex, + bool isprimary, + double reltuples) { Oid relid = RelationGetRelid(rel); Relation pg_class; @@ -1876,15 +1873,6 @@ index_update_stats(Relation rel, dirty = true; } } - if (OidIsValid(reltoastidxid)) - { - Assert(rd_rel->relkind == RELKIND_TOASTVALUE); - if (rd_rel->reltoastidxid != reltoastidxid) - { - rd_rel->reltoastidxid = reltoastidxid; - dirty = true; - } - } if (reltuples >= 0) { @@ -2072,14 +2060,11 @@ index_build(Relation heapRelation, index_update_stats(heapRelation, true, isprimary, - (heapRelation->rd_rel->relkind == RELKIND_TOASTVALUE) ? - RelationGetRelid(indexRelation) : InvalidOid, stats->heap_tuples); index_update_stats(indexRelation, false, false, - InvalidOid, stats->index_tuples); /* Make the updated catalog row versions visible */ diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 81d7c4f..3c2a474 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -473,16 +473,16 @@ CREATE VIEW pg_statio_all_tables AS pg_stat_get_blocks_fetched(T.oid) - pg_stat_get_blocks_hit(T.oid) AS toast_blks_read, pg_stat_get_blocks_hit(T.oid) AS toast_blks_hit, - pg_stat_get_blocks_fetched(X.oid) - - pg_stat_get_blocks_hit(X.oid) AS tidx_blks_read, - pg_stat_get_blocks_hit(X.oid) AS tidx_blks_hit + sum(pg_stat_get_blocks_fetched(X.indexrelid) - + pg_stat_get_blocks_hit(X.indexrelid))::bigint AS tidx_blks_read, + sum(pg_stat_get_blocks_hit(X.indexrelid))::bigint AS tidx_blks_hit FROM pg_class C LEFT JOIN pg_index I ON C.oid = I.indrelid LEFT JOIN pg_class T ON C.reltoastrelid = T.oid LEFT JOIN - pg_class X ON T.reltoastidxid = X.oid + pg_index X ON T.oid = X.indrelid LEFT JOIN pg_namespace N ON (N.oid = C.relnamespace) WHERE C.relkind IN ('r', 't', 'm') - GROUP BY C.oid, N.nspname, C.relname, T.oid, X.oid; + GROUP BY C.oid, N.nspname, C.relname, T.oid, X.indexrelid; CREATE VIEW pg_statio_sys_tables AS SELECT * FROM pg_statio_all_tables diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 095d5e4..e4747a9 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -21,6 +21,7 @@ #include "access/relscan.h" #include "access/rewriteheap.h" #include "access/transam.h" +#include "access/tuptoaster.h" #include "access/xact.h" #include "catalog/catalog.h" #include "catalog/dependency.h" @@ -1172,8 +1173,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class, swaptemp = relform1->reltoastrelid; relform1->reltoastrelid = relform2->reltoastrelid; relform2->reltoastrelid = swaptemp; - - /* we should NOT swap reltoastidxid */ } } else @@ -1393,18 +1392,31 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class, /* * If we're swapping two toast tables by content, do the same for their - * indexes. + * valid index. The swap can actually be safely done only if the relations + * have indexes. */ if (swap_toast_by_content && - relform1->reltoastidxid && relform2->reltoastidxid) - swap_relation_files(relform1->reltoastidxid, - relform2->reltoastidxid, - target_is_pg_class, - swap_toast_by_content, - is_internal, - InvalidTransactionId, - InvalidMultiXactId, - mapped_tables); + relform1->reltoastrelid && + relform2->reltoastrelid) + { + Oid toastIndex1, toastIndex2; + + /* Get valid index for each relation */ + toastIndex1 = toast_get_valid_index(relform1->reltoastrelid, + AccessExclusiveLock); + toastIndex2 = toast_get_valid_index(relform2->reltoastrelid, + AccessExclusiveLock); + + if (toastIndex1 && toastIndex2) + swap_relation_files(toastIndex1, + toastIndex2, + target_is_pg_class, + swap_toast_by_content, + is_internal, + InvalidTransactionId, + InvalidMultiXactId, + mapped_tables); + } /* Clean up. */ heap_freetuple(reltup1); @@ -1528,14 +1540,12 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, newrel = heap_open(OIDOldHeap, NoLock); if (OidIsValid(newrel->rd_rel->reltoastrelid)) { - Relation toastrel; Oid toastidx; char NewToastName[NAMEDATALEN]; - toastrel = relation_open(newrel->rd_rel->reltoastrelid, - AccessShareLock); - toastidx = toastrel->rd_rel->reltoastidxid; - relation_close(toastrel, AccessShareLock); + /* Get the associated valid index to be renamed */ + toastidx = toast_get_valid_index(newrel->rd_rel->reltoastrelid, + AccessShareLock); /* rename the toast table ... */ snprintf(NewToastName, NAMEDATALEN, "pg_toast_%u", @@ -1543,9 +1553,10 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, RenameRelationInternal(newrel->rd_rel->reltoastrelid, NewToastName, true); - /* ... and its index too */ + /* ... and its valid index too. */ snprintf(NewToastName, NAMEDATALEN, "pg_toast_%u_index", OIDOldHeap); + RenameRelationInternal(toastidx, NewToastName, true); } diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c index 8294b29..2b777da 100644 --- a/src/backend/commands/tablecmds.c +++ b/src/backend/commands/tablecmds.c @@ -8728,7 +8728,6 @@ ATExecSetTableSpace(Oid tableOid, Oid newTableSpace, LOCKMODE lockmode) Relation rel; Oid oldTableSpace; Oid reltoastrelid; - Oid reltoastidxid; Oid newrelfilenode; RelFileNode newrnode; SMgrRelation dstrel; @@ -8736,6 +8735,8 @@ ATExecSetTableSpace(Oid tableOid, Oid newTableSpace, LOCKMODE lockmode) HeapTuple tuple; Form_pg_class rd_rel; ForkNumber forkNum; + List *reltoastidxids = NIL; + ListCell *lc; /* * Need lock here in case we are recursing to toast table or index @@ -8782,7 +8783,13 @@ ATExecSetTableSpace(Oid tableOid, Oid newTableSpace, LOCKMODE lockmode) errmsg("cannot move temporary tables of other sessions"))); reltoastrelid = rel->rd_rel->reltoastrelid; - reltoastidxid = rel->rd_rel->reltoastidxid; + /* Fetch the list of indexes on toast relation if necessary */ + if (OidIsValid(reltoastrelid)) + { + Relation toastRel = relation_open(reltoastrelid, lockmode); + reltoastidxids = RelationGetIndexList(toastRel); + relation_close(toastRel, lockmode); + } /* Get a modifiable copy of the relation's pg_class row */ pg_class = heap_open(RelationRelationId, RowExclusiveLock); @@ -8863,8 +8870,15 @@ ATExecSetTableSpace(Oid tableOid, Oid newTableSpace, LOCKMODE lockmode) /* Move associated toast relation and/or index, too */ if (OidIsValid(reltoastrelid)) ATExecSetTableSpace(reltoastrelid, newTableSpace, lockmode); - if (OidIsValid(reltoastidxid)) - ATExecSetTableSpace(reltoastidxid, newTableSpace, lockmode); + foreach(lc, reltoastidxids) + { + Oid toastidxid = lfirst_oid(lc); + if (OidIsValid(toastidxid)) + ATExecSetTableSpace(toastidxid, newTableSpace, lockmode); + } + + /* Clean up */ + list_free(reltoastidxids); } /* diff --git a/src/backend/rewrite/rewriteDefine.c b/src/backend/rewrite/rewriteDefine.c index fb57621..f721dbb 100644 --- a/src/backend/rewrite/rewriteDefine.c +++ b/src/backend/rewrite/rewriteDefine.c @@ -575,8 +575,8 @@ DefineQueryRewrite(char *rulename, /* * Fix pg_class entry to look like a normal view's, including setting - * the correct relkind and removal of reltoastrelid/reltoastidxid of - * the toast table we potentially removed above. + * the correct relkind and removal of reltoastrelid of the toast table + * we potentially removed above. */ classTup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(event_relid)); if (!HeapTupleIsValid(classTup)) @@ -588,7 +588,6 @@ DefineQueryRewrite(char *rulename, classForm->reltuples = 0; classForm->relallvisible = 0; classForm->reltoastrelid = InvalidOid; - classForm->reltoastidxid = InvalidOid; classForm->relhasindex = false; classForm->relkind = RELKIND_VIEW; classForm->relhasoids = false; diff --git a/src/backend/utils/adt/dbsize.c b/src/backend/utils/adt/dbsize.c index 4c4e1ed..bdef79b 100644 --- a/src/backend/utils/adt/dbsize.c +++ b/src/backend/utils/adt/dbsize.c @@ -332,7 +332,7 @@ pg_relation_size(PG_FUNCTION_ARGS) } /* - * Calculate total on-disk size of a TOAST relation, including its index. + * Calculate total on-disk size of a TOAST relation, including its indexes. * Must not be applied to non-TOAST relations. */ static int64 @@ -340,8 +340,9 @@ calculate_toast_table_size(Oid toastrelid) { int64 size = 0; Relation toastRel; - Relation toastIdxRel; ForkNumber forkNum; + ListCell *lc; + List *indexlist; toastRel = relation_open(toastrelid, AccessShareLock); @@ -351,12 +352,21 @@ calculate_toast_table_size(Oid toastrelid) toastRel->rd_backend, forkNum); /* toast index size, including FSM and VM size */ - toastIdxRel = relation_open(toastRel->rd_rel->reltoastidxid, AccessShareLock); - for (forkNum = 0; forkNum <= MAX_FORKNUM; forkNum++) - size += calculate_relation_size(&(toastIdxRel->rd_node), - toastIdxRel->rd_backend, forkNum); + indexlist = RelationGetIndexList(toastRel); - relation_close(toastIdxRel, AccessShareLock); + /* Size is calculated using all the indexes available */ + foreach(lc, indexlist) + { + Relation toastIdxRel; + toastIdxRel = relation_open(lfirst_oid(lc), + AccessShareLock); + for (forkNum = 0; forkNum <= MAX_FORKNUM; forkNum++) + size += calculate_relation_size(&(toastIdxRel->rd_node), + toastIdxRel->rd_backend, forkNum); + + relation_close(toastIdxRel, AccessShareLock); + } + list_free(indexlist); relation_close(toastRel, AccessShareLock); return size; diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index ec956ad..ccd5663 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -2781,16 +2781,16 @@ binary_upgrade_set_pg_class_oids(Archive *fout, Oid pg_class_reltoastidxid; appendPQExpBuffer(upgrade_query, - "SELECT c.reltoastrelid, t.reltoastidxid " + "SELECT c.reltoastrelid, t.indexrelid " "FROM pg_catalog.pg_class c LEFT JOIN " - "pg_catalog.pg_class t ON (c.reltoastrelid = t.oid) " - "WHERE c.oid = '%u'::pg_catalog.oid;", + "pg_catalog.pg_index t ON (c.reltoastrelid = t.indrelid) " + "WHERE c.oid = '%u'::pg_catalog.oid AND t.indisvalid;", pg_class_oid); upgrade_res = ExecuteSqlQueryForSingleRow(fout, upgrade_query->data); pg_class_reltoastrelid = atooid(PQgetvalue(upgrade_res, 0, PQfnumber(upgrade_res, "reltoastrelid"))); - pg_class_reltoastidxid = atooid(PQgetvalue(upgrade_res, 0, PQfnumber(upgrade_res, "reltoastidxid"))); + pg_class_reltoastidxid = atooid(PQgetvalue(upgrade_res, 0, PQfnumber(upgrade_res, "indexrelid"))); appendPQExpBuffer(upgrade_buffer, "\n-- For binary upgrade, must preserve pg_class oids\n"); @@ -2816,7 +2816,7 @@ binary_upgrade_set_pg_class_oids(Archive *fout, "SELECT binary_upgrade.set_next_toast_pg_class_oid('%u'::pg_catalog.oid);\n", pg_class_reltoastrelid); - /* every toast table has an index */ + /* every toast table has one valid index */ appendPQExpBuffer(upgrade_buffer, "SELECT binary_upgrade.set_next_index_pg_class_oid('%u'::pg_catalog.oid);\n", pg_class_reltoastidxid); diff --git a/src/include/access/tuptoaster.h b/src/include/access/tuptoaster.h index 6f4fc45..5890290 100644 --- a/src/include/access/tuptoaster.h +++ b/src/include/access/tuptoaster.h @@ -15,6 +15,7 @@ #include "access/htup_details.h" #include "utils/relcache.h" +#include "storage/lock.h" /* * This enables de-toasting of index entries. Needed until VACUUM is @@ -188,4 +189,12 @@ extern Size toast_raw_datum_size(Datum value); */ extern Size toast_datum_size(Datum value); +/* ---------- + * toast_get_valid_index - + * + * Return valid index associated to a toast relation + * ---------- + */ +extern Oid toast_get_valid_index(Oid toastoid, LOCKMODE lock); + #endif /* TUPTOASTER_H */ diff --git a/src/include/catalog/pg_class.h b/src/include/catalog/pg_class.h index 2225787..49c4f6f 100644 --- a/src/include/catalog/pg_class.h +++ b/src/include/catalog/pg_class.h @@ -48,7 +48,6 @@ CATALOG(pg_class,1259) BKI_BOOTSTRAP BKI_ROWTYPE_OID(83) BKI_SCHEMA_MACRO int32 relallvisible; /* # of all-visible blocks (not always * up-to-date) */ Oid reltoastrelid; /* OID of toast table; 0 if none */ - Oid reltoastidxid; /* if toast table, OID of chunk_id index */ bool relhasindex; /* T if has (or has had) any indexes */ bool relisshared; /* T if shared across databases */ char relpersistence; /* see RELPERSISTENCE_xxx constants below */ @@ -94,7 +93,7 @@ typedef FormData_pg_class *Form_pg_class; * ---------------- */ -#define Natts_pg_class 29 +#define Natts_pg_class 28 #define Anum_pg_class_relname 1 #define Anum_pg_class_relnamespace 2 #define Anum_pg_class_reltype 3 @@ -107,23 +106,22 @@ typedef FormData_pg_class *Form_pg_class; #define Anum_pg_class_reltuples 10 #define Anum_pg_class_relallvisible 11 #define Anum_pg_class_reltoastrelid 12 -#define Anum_pg_class_reltoastidxid 13 -#define Anum_pg_class_relhasindex 14 -#define Anum_pg_class_relisshared 15 -#define Anum_pg_class_relpersistence 16 -#define Anum_pg_class_relkind 17 -#define Anum_pg_class_relnatts 18 -#define Anum_pg_class_relchecks 19 -#define Anum_pg_class_relhasoids 20 -#define Anum_pg_class_relhaspkey 21 -#define Anum_pg_class_relhasrules 22 -#define Anum_pg_class_relhastriggers 23 -#define Anum_pg_class_relhassubclass 24 -#define Anum_pg_class_relispopulated 25 -#define Anum_pg_class_relfrozenxid 26 -#define Anum_pg_class_relminmxid 27 -#define Anum_pg_class_relacl 28 -#define Anum_pg_class_reloptions 29 +#define Anum_pg_class_relhasindex 13 +#define Anum_pg_class_relisshared 14 +#define Anum_pg_class_relpersistence 15 +#define Anum_pg_class_relkind 16 +#define Anum_pg_class_relnatts 17 +#define Anum_pg_class_relchecks 18 +#define Anum_pg_class_relhasoids 19 +#define Anum_pg_class_relhaspkey 20 +#define Anum_pg_class_relhasrules 21 +#define Anum_pg_class_relhastriggers 22 +#define Anum_pg_class_relhassubclass 23 +#define Anum_pg_class_relispopulated 24 +#define Anum_pg_class_relfrozenxid 25 +#define Anum_pg_class_relminmxid 26 +#define Anum_pg_class_relacl 27 +#define Anum_pg_class_reloptions 28 /* ---------------- * initial contents of pg_class @@ -138,13 +136,13 @@ typedef FormData_pg_class *Form_pg_class; * Note: "3" in the relfrozenxid column stands for FirstNormalTransactionId; * similarly, "1" in relminmxid stands for FirstMultiXactId */ -DATA(insert OID = 1247 ( pg_type PGNSP 71 0 PGUID 0 0 0 0 0 0 0 0 f f p r 30 0 t f f f f t 3 1 _null_ _null_ )); +DATA(insert OID = 1247 ( pg_type PGNSP 71 0 PGUID 0 0 0 0 0 0 0 f f p r 30 0 t f f f f t 3 1 _null_ _null_ )); DESCR(""); -DATA(insert OID = 1249 ( pg_attribute PGNSP 75 0 PGUID 0 0 0 0 0 0 0 0 f f p r 21 0 f f f f f t 3 1 _null_ _null_ )); +DATA(insert OID = 1249 ( pg_attribute PGNSP 75 0 PGUID 0 0 0 0 0 0 0 f f p r 21 0 f f f f f t 3 1 _null_ _null_ )); DESCR(""); -DATA(insert OID = 1255 ( pg_proc PGNSP 81 0 PGUID 0 0 0 0 0 0 0 0 f f p r 27 0 t f f f f t 3 1 _null_ _null_ )); +DATA(insert OID = 1255 ( pg_proc PGNSP 81 0 PGUID 0 0 0 0 0 0 0 f f p r 27 0 t f f f f t 3 1 _null_ _null_ )); DESCR(""); -DATA(insert OID = 1259 ( pg_class PGNSP 83 0 PGUID 0 0 0 0 0 0 0 0 f f p r 29 0 t f f f f t 3 1 _null_ _null_ )); +DATA(insert OID = 1259 ( pg_class PGNSP 83 0 PGUID 0 0 0 0 0 0 0 f f p r 28 0 t f f f f t 3 1 _null_ _null_ )); DESCR(""); diff --git a/src/test/regress/expected/oidjoins.out b/src/test/regress/expected/oidjoins.out index 06ed856..6c5cb5a 100644 --- a/src/test/regress/expected/oidjoins.out +++ b/src/test/regress/expected/oidjoins.out @@ -353,14 +353,6 @@ WHERE reltoastrelid != 0 AND ------+--------------- (0 rows) -SELECT ctid, reltoastidxid -FROM pg_catalog.pg_class fk -WHERE reltoastidxid != 0 AND - NOT EXISTS(SELECT 1 FROM pg_catalog.pg_class pk WHERE pk.oid = fk.reltoastidxid); - ctid | reltoastidxid -------+--------------- -(0 rows) - SELECT ctid, collnamespace FROM pg_catalog.pg_collation fk WHERE collnamespace != 0 AND diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out index 57ae842..a6444a0 100644 --- a/src/test/regress/expected/rules.out +++ b/src/test/regress/expected/rules.out @@ -1852,15 +1852,15 @@ SELECT viewname, definition FROM pg_views WHERE schemaname <> 'information_schem | (sum(pg_stat_get_blocks_hit(i.indexrelid)))::bigint AS idx_blks_hit, + | (pg_stat_get_blocks_fetched(t.oid) - pg_stat_get_blocks_hit(t.oid)) AS toast_blks_read, + | pg_stat_get_blocks_hit(t.oid) AS toast_blks_hit, + - | (pg_stat_get_blocks_fetched(x.oid) - pg_stat_get_blocks_hit(x.oid)) AS tidx_blks_read, + - | pg_stat_get_blocks_hit(x.oid) AS tidx_blks_hit + + | (sum((pg_stat_get_blocks_fetched(x.indexrelid) - pg_stat_get_blocks_hit(x.indexrelid))))::bigint AS tidx_blks_read, + + | (sum(pg_stat_get_blocks_hit(x.indexrelid)))::bigint AS tidx_blks_hit + | FROM ((((pg_class c + | LEFT JOIN pg_index i ON ((c.oid = i.indrelid))) + | LEFT JOIN pg_class t ON ((c.reltoastrelid = t.oid))) + - | LEFT JOIN pg_class x ON ((t.reltoastidxid = x.oid))) + + | LEFT JOIN pg_index x ON ((t.oid = x.indrelid))) + | LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace))) + | WHERE (c.relkind = ANY (ARRAY['r'::"char", 't'::"char", 'm'::"char"])) + - | GROUP BY c.oid, n.nspname, c.relname, t.oid, x.oid; + | GROUP BY c.oid, n.nspname, c.relname, t.oid, x.indexrelid; pg_statio_sys_indexes | SELECT pg_statio_all_indexes.relid, + | pg_statio_all_indexes.indexrelid, + | pg_statio_all_indexes.schemaname, + @@ -2347,11 +2347,11 @@ select xmin, * from fooview; -- fail, views don't have such a column ERROR: column "xmin" does not exist LINE 1: select xmin, * from fooview; ^ -select reltoastrelid, reltoastidxid, relkind, relfrozenxid +select reltoastrelid, relkind, relfrozenxid from pg_class where oid = 'fooview'::regclass; - reltoastrelid | reltoastidxid | relkind | relfrozenxid ----------------+---------------+---------+-------------- - 0 | 0 | v | 0 + reltoastrelid | relkind | relfrozenxid +---------------+---------+-------------- + 0 | v | 0 (1 row) drop view fooview; diff --git a/src/test/regress/sql/oidjoins.sql b/src/test/regress/sql/oidjoins.sql index 6422da2..9b91683 100644 --- a/src/test/regress/sql/oidjoins.sql +++ b/src/test/regress/sql/oidjoins.sql @@ -177,10 +177,6 @@ SELECT ctid, reltoastrelid FROM pg_catalog.pg_class fk WHERE reltoastrelid != 0 AND NOT EXISTS(SELECT 1 FROM pg_catalog.pg_class pk WHERE pk.oid = fk.reltoastrelid); -SELECT ctid, reltoastidxid -FROM pg_catalog.pg_class fk -WHERE reltoastidxid != 0 AND - NOT EXISTS(SELECT 1 FROM pg_catalog.pg_class pk WHERE pk.oid = fk.reltoastidxid); SELECT ctid, collnamespace FROM pg_catalog.pg_collation fk WHERE collnamespace != 0 AND diff --git a/src/test/regress/sql/rules.sql b/src/test/regress/sql/rules.sql index d5a3571..6361297 100644 --- a/src/test/regress/sql/rules.sql +++ b/src/test/regress/sql/rules.sql @@ -872,7 +872,7 @@ create rule "_RETURN" as on select to fooview do instead select * from fooview; select xmin, * from fooview; -- fail, views don't have such a column -select reltoastrelid, reltoastidxid, relkind, relfrozenxid +select reltoastrelid, relkind, relfrozenxid from pg_class where oid = 'fooview'::regclass; drop view fooview; diff --git a/src/tools/findoidjoins/README b/src/tools/findoidjoins/README index b5c4d1b..e3e8a2a 100644 --- a/src/tools/findoidjoins/README +++ b/src/tools/findoidjoins/README @@ -86,7 +86,6 @@ Join pg_catalog.pg_class.relowner => pg_catalog.pg_authid.oid Join pg_catalog.pg_class.relam => pg_catalog.pg_am.oid Join pg_catalog.pg_class.reltablespace => pg_catalog.pg_tablespace.oid Join pg_catalog.pg_class.reltoastrelid => pg_catalog.pg_class.oid -Join pg_catalog.pg_class.reltoastidxid => pg_catalog.pg_class.oid Join pg_catalog.pg_collation.collnamespace => pg_catalog.pg_namespace.oid Join pg_catalog.pg_collation.collowner => pg_catalog.pg_authid.oid Join pg_catalog.pg_constraint.connamespace => pg_catalog.pg_namespace.oid