postgresql/src/backend/catalog/pg_publication.c

516 lines
13 KiB
C
Raw Normal View History

/*-------------------------------------------------------------------------
*
* pg_publication.c
* publication C API manipulation
*
* Portions Copyright (c) 1996-2019, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* pg_publication.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "funcapi.h"
#include "miscadmin.h"
#include "access/genam.h"
#include "access/heapam.h"
#include "access/htup_details.h"
tableam: Add and use scan APIs. Too allow table accesses to be not directly dependent on heap, several new abstractions are needed. Specifically: 1) Heap scans need to be generalized into table scans. Do this by introducing TableScanDesc, which will be the "base class" for individual AMs. This contains the AM independent fields from HeapScanDesc. The previous heap_{beginscan,rescan,endscan} et al. have been replaced with a table_ version. There's no direct replacement for heap_getnext(), as that returned a HeapTuple, which is undesirable for a other AMs. Instead there's table_scan_getnextslot(). But note that heap_getnext() lives on, it's still used widely to access catalog tables. This is achieved by new scan_begin, scan_end, scan_rescan, scan_getnextslot callbacks. 2) The portion of parallel scans that's shared between backends need to be able to do so without the user doing per-AM work. To achieve that new parallelscan_{estimate, initialize, reinitialize} callbacks are introduced, which operate on a new ParallelTableScanDesc, which again can be subclassed by AMs. As it is likely that several AMs are going to be block oriented, block oriented callbacks that can be shared between such AMs are provided and used by heap. table_block_parallelscan_{estimate, intiialize, reinitialize} as callbacks, and table_block_parallelscan_{nextpage, init} for use in AMs. These operate on a ParallelBlockTableScanDesc. 3) Index scans need to be able to access tables to return a tuple, and there needs to be state across individual accesses to the heap to store state like buffers. That's now handled by introducing a sort-of-scan IndexFetchTable, which again is intended to be subclassed by individual AMs (for heap IndexFetchHeap). The relevant callbacks for an AM are index_fetch_{end, begin, reset} to create the necessary state, and index_fetch_tuple to retrieve an indexed tuple. Note that index_fetch_tuple implementations need to be smarter than just blindly fetching the tuples for AMs that have optimizations similar to heap's HOT - the currently alive tuple in the update chain needs to be fetched if appropriate. Similar to table_scan_getnextslot(), it's undesirable to continue to return HeapTuples. Thus index_fetch_heap (might want to rename that later) now accepts a slot as an argument. Core code doesn't have a lot of call sites performing index scans without going through the systable_* API (in contrast to loads of heap_getnext calls and working directly with HeapTuples). Index scans now store the result of a search in IndexScanDesc->xs_heaptid, rather than xs_ctup->t_self. As the target is not generally a HeapTuple anymore that seems cleaner. To be able to sensible adapt code to use the above, two further callbacks have been introduced: a) slot_callbacks returns a TupleTableSlotOps* suitable for creating slots capable of holding a tuple of the AMs type. table_slot_callbacks() and table_slot_create() are based upon that, but have additional logic to deal with views, foreign tables, etc. While this change could have been done separately, nearly all the call sites that needed to be adapted for the rest of this commit also would have been needed to be adapted for table_slot_callbacks(), making separation not worthwhile. b) tuple_satisfies_snapshot checks whether the tuple in a slot is currently visible according to a snapshot. That's required as a few places now don't have a buffer + HeapTuple around, but a slot (which in heap's case internally has that information). Additionally a few infrastructure changes were needed: I) SysScanDesc, as used by systable_{beginscan, getnext} et al. now internally uses a slot to keep track of tuples. While systable_getnext() still returns HeapTuples, and will so for the foreseeable future, the index API (see 1) above) now only deals with slots. The remainder, and largest part, of this commit is then adjusting all scans in postgres to use the new APIs. Author: Andres Freund, Haribabu Kommi, Alvaro Herrera Discussion: https://postgr.es/m/20180703070645.wchpu5muyto5n647@alap3.anarazel.de https://postgr.es/m/20160812231527.GA690404@alvherre.pgsql
2019-03-11 20:46:41 +01:00
#include "access/tableam.h"
#include "access/xact.h"
#include "catalog/catalog.h"
#include "catalog/dependency.h"
#include "catalog/index.h"
#include "catalog/indexing.h"
#include "catalog/namespace.h"
#include "catalog/objectaccess.h"
#include "catalog/objectaddress.h"
#include "catalog/pg_type.h"
#include "catalog/pg_publication.h"
#include "catalog/pg_publication_rel.h"
#include "utils/array.h"
#include "utils/builtins.h"
#include "utils/catcache.h"
#include "utils/fmgroids.h"
#include "utils/inval.h"
#include "utils/lsyscache.h"
#include "utils/rel.h"
#include "utils/syscache.h"
/*
* Check if relation can be in given publication and throws appropriate
* error if not.
*/
static void
check_publication_add_relation(Relation targetrel)
{
/* Give more specific error for partitioned tables */
if (RelationGetForm(targetrel)->relkind == RELKIND_PARTITIONED_TABLE)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("\"%s\" is a partitioned table",
RelationGetRelationName(targetrel)),
errdetail("Adding partitioned tables to publications is not supported."),
errhint("You can add the table partitions individually.")));
/* Must be table */
if (RelationGetForm(targetrel)->relkind != RELKIND_RELATION)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("\"%s\" is not a table",
RelationGetRelationName(targetrel)),
errdetail("Only tables can be added to publications.")));
/* Can't be system table */
if (IsCatalogRelation(targetrel))
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("\"%s\" is a system table",
RelationGetRelationName(targetrel)),
errdetail("System tables cannot be added to publications.")));
/* UNLOGGED and TEMP relations cannot be part of publication. */
if (!RelationNeedsWAL(targetrel))
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("table \"%s\" cannot be replicated",
RelationGetRelationName(targetrel)),
errdetail("Temporary and unlogged relations cannot be replicated.")));
}
/*
* Returns if relation represented by oid and Form_pg_class entry
* is publishable.
*
* Does same checks as the above, but does not need relation to be opened
* and also does not throw errors.
*
* Note this also excludes all tables with relid < FirstNormalObjectId,
* ie all tables created during initdb. This mainly affects the preinstalled
* information_schema. (IsCatalogClass() only checks for these inside
* pg_catalog and toast schemas.)
*/
static bool
is_publishable_class(Oid relid, Form_pg_class reltuple)
{
return reltuple->relkind == RELKIND_RELATION &&
!IsCatalogClass(relid, reltuple) &&
reltuple->relpersistence == RELPERSISTENCE_PERMANENT &&
relid >= FirstNormalObjectId;
}
/*
* Another variant of this, taking a Relation.
*/
bool
is_publishable_relation(Relation rel)
{
return is_publishable_class(RelationGetRelid(rel), rel->rd_rel);
}
/*
* SQL-callable variant of the above
*
* This returns null when the relation does not exist. This is intended to be
* used for example in psql to avoid gratuitous errors when there are
* concurrent catalog changes.
*/
Datum
pg_relation_is_publishable(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
HeapTuple tuple;
bool result;
tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(relid));
if (!tuple)
PG_RETURN_NULL();
result = is_publishable_class(relid, (Form_pg_class) GETSTRUCT(tuple));
ReleaseSysCache(tuple);
PG_RETURN_BOOL(result);
}
/*
* Insert new publication / relation mapping.
*/
ObjectAddress
publication_add_relation(Oid pubid, Relation targetrel,
bool if_not_exists)
{
Relation rel;
HeapTuple tup;
Datum values[Natts_pg_publication_rel];
bool nulls[Natts_pg_publication_rel];
Oid relid = RelationGetRelid(targetrel);
Oid prrelid;
Publication *pub = GetPublication(pubid);
ObjectAddress myself,
referenced;
rel = table_open(PublicationRelRelationId, RowExclusiveLock);
/*
* Check for duplicates. Note that this does not really prevent
* duplicates, it's here just to provide nicer error message in common
* case. The real protection is the unique key on the catalog.
*/
if (SearchSysCacheExists2(PUBLICATIONRELMAP, ObjectIdGetDatum(relid),
ObjectIdGetDatum(pubid)))
{
table_close(rel, RowExclusiveLock);
if (if_not_exists)
return InvalidObjectAddress;
ereport(ERROR,
(errcode(ERRCODE_DUPLICATE_OBJECT),
errmsg("relation \"%s\" is already member of publication \"%s\"",
RelationGetRelationName(targetrel), pub->name)));
}
check_publication_add_relation(targetrel);
/* Form a tuple. */
memset(values, 0, sizeof(values));
memset(nulls, false, sizeof(nulls));
Remove WITH OIDS support, change oid catalog column visibility. Previously tables declared WITH OIDS, including a significant fraction of the catalog tables, stored the oid column not as a normal column, but as part of the tuple header. This special column was not shown by default, which was somewhat odd, as it's often (consider e.g. pg_class.oid) one of the more important parts of a row. Neither pg_dump nor COPY included the contents of the oid column by default. The fact that the oid column was not an ordinary column necessitated a significant amount of special case code to support oid columns. That already was painful for the existing, but upcoming work aiming to make table storage pluggable, would have required expanding and duplicating that "specialness" significantly. WITH OIDS has been deprecated since 2005 (commit ff02d0a05280e0). Remove it. Removing includes: - CREATE TABLE and ALTER TABLE syntax for declaring the table to be WITH OIDS has been removed (WITH (oids[ = true]) will error out) - pg_dump does not support dumping tables declared WITH OIDS and will issue a warning when dumping one (and ignore the oid column). - restoring an pg_dump archive with pg_restore will warn when restoring a table with oid contents (and ignore the oid column) - COPY will refuse to load binary dump that includes oids. - pg_upgrade will error out when encountering tables declared WITH OIDS, they have to be altered to remove the oid column first. - Functionality to access the oid of the last inserted row (like plpgsql's RESULT_OID, spi's SPI_lastoid, ...) has been removed. The syntax for declaring a table WITHOUT OIDS (or WITH (oids = false) for CREATE TABLE) is still supported. While that requires a bit of support code, it seems unnecessary to break applications / dumps that do not use oids, and are explicit about not using them. The biggest user of WITH OID columns was postgres' catalog. This commit changes all 'magic' oid columns to be columns that are normally declared and stored. To reduce unnecessary query breakage all the newly added columns are still named 'oid', even if a table's column naming scheme would indicate 'reloid' or such. This obviously requires adapting a lot code, mostly replacing oid access via HeapTupleGetOid() with access to the underlying Form_pg_*->oid column. The bootstrap process now assigns oids for all oid columns in genbki.pl that do not have an explicit value (starting at the largest oid previously used), only oids assigned later by oids will be above FirstBootstrapObjectId. As the oid column now is a normal column the special bootstrap syntax for oids has been removed. Oids are not automatically assigned during insertion anymore, all backend code explicitly assigns oids with GetNewOidWithIndex(). For the rare case that insertions into the catalog via SQL are called for the new pg_nextoid() function can be used (which only works on catalog tables). The fact that oid columns on system tables are now normal columns means that they will be included in the set of columns expanded by * (i.e. SELECT * FROM pg_class will now include the table's oid, previously it did not). It'd not technically be hard to hide oid column by default, but that'd mean confusing behavior would either have to be carried forward forever, or it'd cause breakage down the line. While it's not unlikely that further adjustments are needed, the scope/invasiveness of the patch makes it worthwhile to get merge this now. It's painful to maintain externally, too complicated to commit after the code code freeze, and a dependency of a number of other patches. Catversion bump, for obvious reasons. Author: Andres Freund, with contributions by John Naylor Discussion: https://postgr.es/m/20180930034810.ywp2c7awz7opzcfr@alap3.anarazel.de
2018-11-21 00:36:57 +01:00
prrelid = GetNewOidWithIndex(rel, PublicationRelObjectIndexId,
Anum_pg_publication_rel_oid);
values[Anum_pg_publication_rel_oid - 1] = ObjectIdGetDatum(prrelid);
values[Anum_pg_publication_rel_prpubid - 1] =
ObjectIdGetDatum(pubid);
values[Anum_pg_publication_rel_prrelid - 1] =
ObjectIdGetDatum(relid);
tup = heap_form_tuple(RelationGetDescr(rel), values, nulls);
/* Insert tuple into catalog. */
Remove WITH OIDS support, change oid catalog column visibility. Previously tables declared WITH OIDS, including a significant fraction of the catalog tables, stored the oid column not as a normal column, but as part of the tuple header. This special column was not shown by default, which was somewhat odd, as it's often (consider e.g. pg_class.oid) one of the more important parts of a row. Neither pg_dump nor COPY included the contents of the oid column by default. The fact that the oid column was not an ordinary column necessitated a significant amount of special case code to support oid columns. That already was painful for the existing, but upcoming work aiming to make table storage pluggable, would have required expanding and duplicating that "specialness" significantly. WITH OIDS has been deprecated since 2005 (commit ff02d0a05280e0). Remove it. Removing includes: - CREATE TABLE and ALTER TABLE syntax for declaring the table to be WITH OIDS has been removed (WITH (oids[ = true]) will error out) - pg_dump does not support dumping tables declared WITH OIDS and will issue a warning when dumping one (and ignore the oid column). - restoring an pg_dump archive with pg_restore will warn when restoring a table with oid contents (and ignore the oid column) - COPY will refuse to load binary dump that includes oids. - pg_upgrade will error out when encountering tables declared WITH OIDS, they have to be altered to remove the oid column first. - Functionality to access the oid of the last inserted row (like plpgsql's RESULT_OID, spi's SPI_lastoid, ...) has been removed. The syntax for declaring a table WITHOUT OIDS (or WITH (oids = false) for CREATE TABLE) is still supported. While that requires a bit of support code, it seems unnecessary to break applications / dumps that do not use oids, and are explicit about not using them. The biggest user of WITH OID columns was postgres' catalog. This commit changes all 'magic' oid columns to be columns that are normally declared and stored. To reduce unnecessary query breakage all the newly added columns are still named 'oid', even if a table's column naming scheme would indicate 'reloid' or such. This obviously requires adapting a lot code, mostly replacing oid access via HeapTupleGetOid() with access to the underlying Form_pg_*->oid column. The bootstrap process now assigns oids for all oid columns in genbki.pl that do not have an explicit value (starting at the largest oid previously used), only oids assigned later by oids will be above FirstBootstrapObjectId. As the oid column now is a normal column the special bootstrap syntax for oids has been removed. Oids are not automatically assigned during insertion anymore, all backend code explicitly assigns oids with GetNewOidWithIndex(). For the rare case that insertions into the catalog via SQL are called for the new pg_nextoid() function can be used (which only works on catalog tables). The fact that oid columns on system tables are now normal columns means that they will be included in the set of columns expanded by * (i.e. SELECT * FROM pg_class will now include the table's oid, previously it did not). It'd not technically be hard to hide oid column by default, but that'd mean confusing behavior would either have to be carried forward forever, or it'd cause breakage down the line. While it's not unlikely that further adjustments are needed, the scope/invasiveness of the patch makes it worthwhile to get merge this now. It's painful to maintain externally, too complicated to commit after the code code freeze, and a dependency of a number of other patches. Catversion bump, for obvious reasons. Author: Andres Freund, with contributions by John Naylor Discussion: https://postgr.es/m/20180930034810.ywp2c7awz7opzcfr@alap3.anarazel.de
2018-11-21 00:36:57 +01:00
CatalogTupleInsert(rel, tup);
heap_freetuple(tup);
ObjectAddressSet(myself, PublicationRelRelationId, prrelid);
/* Add dependency on the publication */
ObjectAddressSet(referenced, PublicationRelationId, pubid);
recordDependencyOn(&myself, &referenced, DEPENDENCY_AUTO);
/* Add dependency on the relation */
ObjectAddressSet(referenced, RelationRelationId, relid);
recordDependencyOn(&myself, &referenced, DEPENDENCY_AUTO);
/* Close the table. */
table_close(rel, RowExclusiveLock);
/* Invalidate relcache so that publication info is rebuilt. */
CacheInvalidateRelcache(targetrel);
return myself;
}
/*
* Gets list of publication oids for a relation oid.
*/
List *
GetRelationPublications(Oid relid)
{
List *result = NIL;
CatCList *pubrellist;
int i;
/* Find all publications associated with the relation. */
pubrellist = SearchSysCacheList1(PUBLICATIONRELMAP,
ObjectIdGetDatum(relid));
for (i = 0; i < pubrellist->n_members; i++)
{
HeapTuple tup = &pubrellist->members[i]->tuple;
Oid pubid = ((Form_pg_publication_rel) GETSTRUCT(tup))->prpubid;
result = lappend_oid(result, pubid);
}
ReleaseSysCacheList(pubrellist);
return result;
}
/*
* Gets list of relation oids for a publication.
*
* This should only be used for normal publications, the FOR ALL TABLES
* should use GetAllTablesPublicationRelations().
*/
List *
GetPublicationRelations(Oid pubid)
{
List *result;
Relation pubrelsrel;
ScanKeyData scankey;
SysScanDesc scan;
HeapTuple tup;
/* Find all publications associated with the relation. */
pubrelsrel = table_open(PublicationRelRelationId, AccessShareLock);
ScanKeyInit(&scankey,
Anum_pg_publication_rel_prpubid,
BTEqualStrategyNumber, F_OIDEQ,
ObjectIdGetDatum(pubid));
scan = systable_beginscan(pubrelsrel, PublicationRelPrrelidPrpubidIndexId,
true, NULL, 1, &scankey);
result = NIL;
while (HeapTupleIsValid(tup = systable_getnext(scan)))
{
Form_pg_publication_rel pubrel;
pubrel = (Form_pg_publication_rel) GETSTRUCT(tup);
result = lappend_oid(result, pubrel->prrelid);
}
systable_endscan(scan);
table_close(pubrelsrel, AccessShareLock);
return result;
}
/*
* Gets list of publication oids for publications marked as FOR ALL TABLES.
*/
List *
GetAllTablesPublications(void)
{
List *result;
Relation rel;
ScanKeyData scankey;
SysScanDesc scan;
HeapTuple tup;
/* Find all publications that are marked as for all tables. */
rel = table_open(PublicationRelationId, AccessShareLock);
ScanKeyInit(&scankey,
Anum_pg_publication_puballtables,
BTEqualStrategyNumber, F_BOOLEQ,
BoolGetDatum(true));
scan = systable_beginscan(rel, InvalidOid, false,
NULL, 1, &scankey);
result = NIL;
while (HeapTupleIsValid(tup = systable_getnext(scan)))
Remove WITH OIDS support, change oid catalog column visibility. Previously tables declared WITH OIDS, including a significant fraction of the catalog tables, stored the oid column not as a normal column, but as part of the tuple header. This special column was not shown by default, which was somewhat odd, as it's often (consider e.g. pg_class.oid) one of the more important parts of a row. Neither pg_dump nor COPY included the contents of the oid column by default. The fact that the oid column was not an ordinary column necessitated a significant amount of special case code to support oid columns. That already was painful for the existing, but upcoming work aiming to make table storage pluggable, would have required expanding and duplicating that "specialness" significantly. WITH OIDS has been deprecated since 2005 (commit ff02d0a05280e0). Remove it. Removing includes: - CREATE TABLE and ALTER TABLE syntax for declaring the table to be WITH OIDS has been removed (WITH (oids[ = true]) will error out) - pg_dump does not support dumping tables declared WITH OIDS and will issue a warning when dumping one (and ignore the oid column). - restoring an pg_dump archive with pg_restore will warn when restoring a table with oid contents (and ignore the oid column) - COPY will refuse to load binary dump that includes oids. - pg_upgrade will error out when encountering tables declared WITH OIDS, they have to be altered to remove the oid column first. - Functionality to access the oid of the last inserted row (like plpgsql's RESULT_OID, spi's SPI_lastoid, ...) has been removed. The syntax for declaring a table WITHOUT OIDS (or WITH (oids = false) for CREATE TABLE) is still supported. While that requires a bit of support code, it seems unnecessary to break applications / dumps that do not use oids, and are explicit about not using them. The biggest user of WITH OID columns was postgres' catalog. This commit changes all 'magic' oid columns to be columns that are normally declared and stored. To reduce unnecessary query breakage all the newly added columns are still named 'oid', even if a table's column naming scheme would indicate 'reloid' or such. This obviously requires adapting a lot code, mostly replacing oid access via HeapTupleGetOid() with access to the underlying Form_pg_*->oid column. The bootstrap process now assigns oids for all oid columns in genbki.pl that do not have an explicit value (starting at the largest oid previously used), only oids assigned later by oids will be above FirstBootstrapObjectId. As the oid column now is a normal column the special bootstrap syntax for oids has been removed. Oids are not automatically assigned during insertion anymore, all backend code explicitly assigns oids with GetNewOidWithIndex(). For the rare case that insertions into the catalog via SQL are called for the new pg_nextoid() function can be used (which only works on catalog tables). The fact that oid columns on system tables are now normal columns means that they will be included in the set of columns expanded by * (i.e. SELECT * FROM pg_class will now include the table's oid, previously it did not). It'd not technically be hard to hide oid column by default, but that'd mean confusing behavior would either have to be carried forward forever, or it'd cause breakage down the line. While it's not unlikely that further adjustments are needed, the scope/invasiveness of the patch makes it worthwhile to get merge this now. It's painful to maintain externally, too complicated to commit after the code code freeze, and a dependency of a number of other patches. Catversion bump, for obvious reasons. Author: Andres Freund, with contributions by John Naylor Discussion: https://postgr.es/m/20180930034810.ywp2c7awz7opzcfr@alap3.anarazel.de
2018-11-21 00:36:57 +01:00
{
Oid oid = ((Form_pg_publication) GETSTRUCT(tup))->oid;
result = lappend_oid(result, oid);
}
systable_endscan(scan);
table_close(rel, AccessShareLock);
return result;
}
/*
* Gets list of all relation published by FOR ALL TABLES publication(s).
*/
List *
GetAllTablesPublicationRelations(void)
{
Relation classRel;
ScanKeyData key[1];
tableam: Add and use scan APIs. Too allow table accesses to be not directly dependent on heap, several new abstractions are needed. Specifically: 1) Heap scans need to be generalized into table scans. Do this by introducing TableScanDesc, which will be the "base class" for individual AMs. This contains the AM independent fields from HeapScanDesc. The previous heap_{beginscan,rescan,endscan} et al. have been replaced with a table_ version. There's no direct replacement for heap_getnext(), as that returned a HeapTuple, which is undesirable for a other AMs. Instead there's table_scan_getnextslot(). But note that heap_getnext() lives on, it's still used widely to access catalog tables. This is achieved by new scan_begin, scan_end, scan_rescan, scan_getnextslot callbacks. 2) The portion of parallel scans that's shared between backends need to be able to do so without the user doing per-AM work. To achieve that new parallelscan_{estimate, initialize, reinitialize} callbacks are introduced, which operate on a new ParallelTableScanDesc, which again can be subclassed by AMs. As it is likely that several AMs are going to be block oriented, block oriented callbacks that can be shared between such AMs are provided and used by heap. table_block_parallelscan_{estimate, intiialize, reinitialize} as callbacks, and table_block_parallelscan_{nextpage, init} for use in AMs. These operate on a ParallelBlockTableScanDesc. 3) Index scans need to be able to access tables to return a tuple, and there needs to be state across individual accesses to the heap to store state like buffers. That's now handled by introducing a sort-of-scan IndexFetchTable, which again is intended to be subclassed by individual AMs (for heap IndexFetchHeap). The relevant callbacks for an AM are index_fetch_{end, begin, reset} to create the necessary state, and index_fetch_tuple to retrieve an indexed tuple. Note that index_fetch_tuple implementations need to be smarter than just blindly fetching the tuples for AMs that have optimizations similar to heap's HOT - the currently alive tuple in the update chain needs to be fetched if appropriate. Similar to table_scan_getnextslot(), it's undesirable to continue to return HeapTuples. Thus index_fetch_heap (might want to rename that later) now accepts a slot as an argument. Core code doesn't have a lot of call sites performing index scans without going through the systable_* API (in contrast to loads of heap_getnext calls and working directly with HeapTuples). Index scans now store the result of a search in IndexScanDesc->xs_heaptid, rather than xs_ctup->t_self. As the target is not generally a HeapTuple anymore that seems cleaner. To be able to sensible adapt code to use the above, two further callbacks have been introduced: a) slot_callbacks returns a TupleTableSlotOps* suitable for creating slots capable of holding a tuple of the AMs type. table_slot_callbacks() and table_slot_create() are based upon that, but have additional logic to deal with views, foreign tables, etc. While this change could have been done separately, nearly all the call sites that needed to be adapted for the rest of this commit also would have been needed to be adapted for table_slot_callbacks(), making separation not worthwhile. b) tuple_satisfies_snapshot checks whether the tuple in a slot is currently visible according to a snapshot. That's required as a few places now don't have a buffer + HeapTuple around, but a slot (which in heap's case internally has that information). Additionally a few infrastructure changes were needed: I) SysScanDesc, as used by systable_{beginscan, getnext} et al. now internally uses a slot to keep track of tuples. While systable_getnext() still returns HeapTuples, and will so for the foreseeable future, the index API (see 1) above) now only deals with slots. The remainder, and largest part, of this commit is then adjusting all scans in postgres to use the new APIs. Author: Andres Freund, Haribabu Kommi, Alvaro Herrera Discussion: https://postgr.es/m/20180703070645.wchpu5muyto5n647@alap3.anarazel.de https://postgr.es/m/20160812231527.GA690404@alvherre.pgsql
2019-03-11 20:46:41 +01:00
TableScanDesc scan;
HeapTuple tuple;
List *result = NIL;
classRel = table_open(RelationRelationId, AccessShareLock);
ScanKeyInit(&key[0],
Anum_pg_class_relkind,
BTEqualStrategyNumber, F_CHAREQ,
CharGetDatum(RELKIND_RELATION));
tableam: Add and use scan APIs. Too allow table accesses to be not directly dependent on heap, several new abstractions are needed. Specifically: 1) Heap scans need to be generalized into table scans. Do this by introducing TableScanDesc, which will be the "base class" for individual AMs. This contains the AM independent fields from HeapScanDesc. The previous heap_{beginscan,rescan,endscan} et al. have been replaced with a table_ version. There's no direct replacement for heap_getnext(), as that returned a HeapTuple, which is undesirable for a other AMs. Instead there's table_scan_getnextslot(). But note that heap_getnext() lives on, it's still used widely to access catalog tables. This is achieved by new scan_begin, scan_end, scan_rescan, scan_getnextslot callbacks. 2) The portion of parallel scans that's shared between backends need to be able to do so without the user doing per-AM work. To achieve that new parallelscan_{estimate, initialize, reinitialize} callbacks are introduced, which operate on a new ParallelTableScanDesc, which again can be subclassed by AMs. As it is likely that several AMs are going to be block oriented, block oriented callbacks that can be shared between such AMs are provided and used by heap. table_block_parallelscan_{estimate, intiialize, reinitialize} as callbacks, and table_block_parallelscan_{nextpage, init} for use in AMs. These operate on a ParallelBlockTableScanDesc. 3) Index scans need to be able to access tables to return a tuple, and there needs to be state across individual accesses to the heap to store state like buffers. That's now handled by introducing a sort-of-scan IndexFetchTable, which again is intended to be subclassed by individual AMs (for heap IndexFetchHeap). The relevant callbacks for an AM are index_fetch_{end, begin, reset} to create the necessary state, and index_fetch_tuple to retrieve an indexed tuple. Note that index_fetch_tuple implementations need to be smarter than just blindly fetching the tuples for AMs that have optimizations similar to heap's HOT - the currently alive tuple in the update chain needs to be fetched if appropriate. Similar to table_scan_getnextslot(), it's undesirable to continue to return HeapTuples. Thus index_fetch_heap (might want to rename that later) now accepts a slot as an argument. Core code doesn't have a lot of call sites performing index scans without going through the systable_* API (in contrast to loads of heap_getnext calls and working directly with HeapTuples). Index scans now store the result of a search in IndexScanDesc->xs_heaptid, rather than xs_ctup->t_self. As the target is not generally a HeapTuple anymore that seems cleaner. To be able to sensible adapt code to use the above, two further callbacks have been introduced: a) slot_callbacks returns a TupleTableSlotOps* suitable for creating slots capable of holding a tuple of the AMs type. table_slot_callbacks() and table_slot_create() are based upon that, but have additional logic to deal with views, foreign tables, etc. While this change could have been done separately, nearly all the call sites that needed to be adapted for the rest of this commit also would have been needed to be adapted for table_slot_callbacks(), making separation not worthwhile. b) tuple_satisfies_snapshot checks whether the tuple in a slot is currently visible according to a snapshot. That's required as a few places now don't have a buffer + HeapTuple around, but a slot (which in heap's case internally has that information). Additionally a few infrastructure changes were needed: I) SysScanDesc, as used by systable_{beginscan, getnext} et al. now internally uses a slot to keep track of tuples. While systable_getnext() still returns HeapTuples, and will so for the foreseeable future, the index API (see 1) above) now only deals with slots. The remainder, and largest part, of this commit is then adjusting all scans in postgres to use the new APIs. Author: Andres Freund, Haribabu Kommi, Alvaro Herrera Discussion: https://postgr.es/m/20180703070645.wchpu5muyto5n647@alap3.anarazel.de https://postgr.es/m/20160812231527.GA690404@alvherre.pgsql
2019-03-11 20:46:41 +01:00
scan = table_beginscan_catalog(classRel, 1, key);
while ((tuple = heap_getnext(scan, ForwardScanDirection)) != NULL)
{
Form_pg_class relForm = (Form_pg_class) GETSTRUCT(tuple);
Remove WITH OIDS support, change oid catalog column visibility. Previously tables declared WITH OIDS, including a significant fraction of the catalog tables, stored the oid column not as a normal column, but as part of the tuple header. This special column was not shown by default, which was somewhat odd, as it's often (consider e.g. pg_class.oid) one of the more important parts of a row. Neither pg_dump nor COPY included the contents of the oid column by default. The fact that the oid column was not an ordinary column necessitated a significant amount of special case code to support oid columns. That already was painful for the existing, but upcoming work aiming to make table storage pluggable, would have required expanding and duplicating that "specialness" significantly. WITH OIDS has been deprecated since 2005 (commit ff02d0a05280e0). Remove it. Removing includes: - CREATE TABLE and ALTER TABLE syntax for declaring the table to be WITH OIDS has been removed (WITH (oids[ = true]) will error out) - pg_dump does not support dumping tables declared WITH OIDS and will issue a warning when dumping one (and ignore the oid column). - restoring an pg_dump archive with pg_restore will warn when restoring a table with oid contents (and ignore the oid column) - COPY will refuse to load binary dump that includes oids. - pg_upgrade will error out when encountering tables declared WITH OIDS, they have to be altered to remove the oid column first. - Functionality to access the oid of the last inserted row (like plpgsql's RESULT_OID, spi's SPI_lastoid, ...) has been removed. The syntax for declaring a table WITHOUT OIDS (or WITH (oids = false) for CREATE TABLE) is still supported. While that requires a bit of support code, it seems unnecessary to break applications / dumps that do not use oids, and are explicit about not using them. The biggest user of WITH OID columns was postgres' catalog. This commit changes all 'magic' oid columns to be columns that are normally declared and stored. To reduce unnecessary query breakage all the newly added columns are still named 'oid', even if a table's column naming scheme would indicate 'reloid' or such. This obviously requires adapting a lot code, mostly replacing oid access via HeapTupleGetOid() with access to the underlying Form_pg_*->oid column. The bootstrap process now assigns oids for all oid columns in genbki.pl that do not have an explicit value (starting at the largest oid previously used), only oids assigned later by oids will be above FirstBootstrapObjectId. As the oid column now is a normal column the special bootstrap syntax for oids has been removed. Oids are not automatically assigned during insertion anymore, all backend code explicitly assigns oids with GetNewOidWithIndex(). For the rare case that insertions into the catalog via SQL are called for the new pg_nextoid() function can be used (which only works on catalog tables). The fact that oid columns on system tables are now normal columns means that they will be included in the set of columns expanded by * (i.e. SELECT * FROM pg_class will now include the table's oid, previously it did not). It'd not technically be hard to hide oid column by default, but that'd mean confusing behavior would either have to be carried forward forever, or it'd cause breakage down the line. While it's not unlikely that further adjustments are needed, the scope/invasiveness of the patch makes it worthwhile to get merge this now. It's painful to maintain externally, too complicated to commit after the code code freeze, and a dependency of a number of other patches. Catversion bump, for obvious reasons. Author: Andres Freund, with contributions by John Naylor Discussion: https://postgr.es/m/20180930034810.ywp2c7awz7opzcfr@alap3.anarazel.de
2018-11-21 00:36:57 +01:00
Oid relid = relForm->oid;
if (is_publishable_class(relid, relForm))
result = lappend_oid(result, relid);
}
tableam: Add and use scan APIs. Too allow table accesses to be not directly dependent on heap, several new abstractions are needed. Specifically: 1) Heap scans need to be generalized into table scans. Do this by introducing TableScanDesc, which will be the "base class" for individual AMs. This contains the AM independent fields from HeapScanDesc. The previous heap_{beginscan,rescan,endscan} et al. have been replaced with a table_ version. There's no direct replacement for heap_getnext(), as that returned a HeapTuple, which is undesirable for a other AMs. Instead there's table_scan_getnextslot(). But note that heap_getnext() lives on, it's still used widely to access catalog tables. This is achieved by new scan_begin, scan_end, scan_rescan, scan_getnextslot callbacks. 2) The portion of parallel scans that's shared between backends need to be able to do so without the user doing per-AM work. To achieve that new parallelscan_{estimate, initialize, reinitialize} callbacks are introduced, which operate on a new ParallelTableScanDesc, which again can be subclassed by AMs. As it is likely that several AMs are going to be block oriented, block oriented callbacks that can be shared between such AMs are provided and used by heap. table_block_parallelscan_{estimate, intiialize, reinitialize} as callbacks, and table_block_parallelscan_{nextpage, init} for use in AMs. These operate on a ParallelBlockTableScanDesc. 3) Index scans need to be able to access tables to return a tuple, and there needs to be state across individual accesses to the heap to store state like buffers. That's now handled by introducing a sort-of-scan IndexFetchTable, which again is intended to be subclassed by individual AMs (for heap IndexFetchHeap). The relevant callbacks for an AM are index_fetch_{end, begin, reset} to create the necessary state, and index_fetch_tuple to retrieve an indexed tuple. Note that index_fetch_tuple implementations need to be smarter than just blindly fetching the tuples for AMs that have optimizations similar to heap's HOT - the currently alive tuple in the update chain needs to be fetched if appropriate. Similar to table_scan_getnextslot(), it's undesirable to continue to return HeapTuples. Thus index_fetch_heap (might want to rename that later) now accepts a slot as an argument. Core code doesn't have a lot of call sites performing index scans without going through the systable_* API (in contrast to loads of heap_getnext calls and working directly with HeapTuples). Index scans now store the result of a search in IndexScanDesc->xs_heaptid, rather than xs_ctup->t_self. As the target is not generally a HeapTuple anymore that seems cleaner. To be able to sensible adapt code to use the above, two further callbacks have been introduced: a) slot_callbacks returns a TupleTableSlotOps* suitable for creating slots capable of holding a tuple of the AMs type. table_slot_callbacks() and table_slot_create() are based upon that, but have additional logic to deal with views, foreign tables, etc. While this change could have been done separately, nearly all the call sites that needed to be adapted for the rest of this commit also would have been needed to be adapted for table_slot_callbacks(), making separation not worthwhile. b) tuple_satisfies_snapshot checks whether the tuple in a slot is currently visible according to a snapshot. That's required as a few places now don't have a buffer + HeapTuple around, but a slot (which in heap's case internally has that information). Additionally a few infrastructure changes were needed: I) SysScanDesc, as used by systable_{beginscan, getnext} et al. now internally uses a slot to keep track of tuples. While systable_getnext() still returns HeapTuples, and will so for the foreseeable future, the index API (see 1) above) now only deals with slots. The remainder, and largest part, of this commit is then adjusting all scans in postgres to use the new APIs. Author: Andres Freund, Haribabu Kommi, Alvaro Herrera Discussion: https://postgr.es/m/20180703070645.wchpu5muyto5n647@alap3.anarazel.de https://postgr.es/m/20160812231527.GA690404@alvherre.pgsql
2019-03-11 20:46:41 +01:00
table_endscan(scan);
table_close(classRel, AccessShareLock);
return result;
}
/*
* Get publication using oid
*
* The Publication struct and its data are palloc'ed here.
*/
Publication *
GetPublication(Oid pubid)
{
HeapTuple tup;
Publication *pub;
Form_pg_publication pubform;
tup = SearchSysCache1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
if (!HeapTupleIsValid(tup))
elog(ERROR, "cache lookup failed for publication %u", pubid);
pubform = (Form_pg_publication) GETSTRUCT(tup);
pub = (Publication *) palloc(sizeof(Publication));
pub->oid = pubid;
pub->name = pstrdup(NameStr(pubform->pubname));
pub->alltables = pubform->puballtables;
pub->pubactions.pubinsert = pubform->pubinsert;
pub->pubactions.pubupdate = pubform->pubupdate;
pub->pubactions.pubdelete = pubform->pubdelete;
pub->pubactions.pubtruncate = pubform->pubtruncate;
ReleaseSysCache(tup);
return pub;
}
/*
* Get Publication using name.
*/
Publication *
GetPublicationByName(const char *pubname, bool missing_ok)
{
Oid oid;
Remove WITH OIDS support, change oid catalog column visibility. Previously tables declared WITH OIDS, including a significant fraction of the catalog tables, stored the oid column not as a normal column, but as part of the tuple header. This special column was not shown by default, which was somewhat odd, as it's often (consider e.g. pg_class.oid) one of the more important parts of a row. Neither pg_dump nor COPY included the contents of the oid column by default. The fact that the oid column was not an ordinary column necessitated a significant amount of special case code to support oid columns. That already was painful for the existing, but upcoming work aiming to make table storage pluggable, would have required expanding and duplicating that "specialness" significantly. WITH OIDS has been deprecated since 2005 (commit ff02d0a05280e0). Remove it. Removing includes: - CREATE TABLE and ALTER TABLE syntax for declaring the table to be WITH OIDS has been removed (WITH (oids[ = true]) will error out) - pg_dump does not support dumping tables declared WITH OIDS and will issue a warning when dumping one (and ignore the oid column). - restoring an pg_dump archive with pg_restore will warn when restoring a table with oid contents (and ignore the oid column) - COPY will refuse to load binary dump that includes oids. - pg_upgrade will error out when encountering tables declared WITH OIDS, they have to be altered to remove the oid column first. - Functionality to access the oid of the last inserted row (like plpgsql's RESULT_OID, spi's SPI_lastoid, ...) has been removed. The syntax for declaring a table WITHOUT OIDS (or WITH (oids = false) for CREATE TABLE) is still supported. While that requires a bit of support code, it seems unnecessary to break applications / dumps that do not use oids, and are explicit about not using them. The biggest user of WITH OID columns was postgres' catalog. This commit changes all 'magic' oid columns to be columns that are normally declared and stored. To reduce unnecessary query breakage all the newly added columns are still named 'oid', even if a table's column naming scheme would indicate 'reloid' or such. This obviously requires adapting a lot code, mostly replacing oid access via HeapTupleGetOid() with access to the underlying Form_pg_*->oid column. The bootstrap process now assigns oids for all oid columns in genbki.pl that do not have an explicit value (starting at the largest oid previously used), only oids assigned later by oids will be above FirstBootstrapObjectId. As the oid column now is a normal column the special bootstrap syntax for oids has been removed. Oids are not automatically assigned during insertion anymore, all backend code explicitly assigns oids with GetNewOidWithIndex(). For the rare case that insertions into the catalog via SQL are called for the new pg_nextoid() function can be used (which only works on catalog tables). The fact that oid columns on system tables are now normal columns means that they will be included in the set of columns expanded by * (i.e. SELECT * FROM pg_class will now include the table's oid, previously it did not). It'd not technically be hard to hide oid column by default, but that'd mean confusing behavior would either have to be carried forward forever, or it'd cause breakage down the line. While it's not unlikely that further adjustments are needed, the scope/invasiveness of the patch makes it worthwhile to get merge this now. It's painful to maintain externally, too complicated to commit after the code code freeze, and a dependency of a number of other patches. Catversion bump, for obvious reasons. Author: Andres Freund, with contributions by John Naylor Discussion: https://postgr.es/m/20180930034810.ywp2c7awz7opzcfr@alap3.anarazel.de
2018-11-21 00:36:57 +01:00
oid = GetSysCacheOid1(PUBLICATIONNAME, Anum_pg_publication_oid,
CStringGetDatum(pubname));
if (!OidIsValid(oid))
{
if (missing_ok)
return NULL;
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_OBJECT),
errmsg("publication \"%s\" does not exist", pubname)));
}
return GetPublication(oid);
}
/*
* get_publication_oid - given a publication name, look up the OID
*
* If missing_ok is false, throw an error if name not found. If true, just
* return InvalidOid.
*/
Oid
get_publication_oid(const char *pubname, bool missing_ok)
{
Oid oid;
Remove WITH OIDS support, change oid catalog column visibility. Previously tables declared WITH OIDS, including a significant fraction of the catalog tables, stored the oid column not as a normal column, but as part of the tuple header. This special column was not shown by default, which was somewhat odd, as it's often (consider e.g. pg_class.oid) one of the more important parts of a row. Neither pg_dump nor COPY included the contents of the oid column by default. The fact that the oid column was not an ordinary column necessitated a significant amount of special case code to support oid columns. That already was painful for the existing, but upcoming work aiming to make table storage pluggable, would have required expanding and duplicating that "specialness" significantly. WITH OIDS has been deprecated since 2005 (commit ff02d0a05280e0). Remove it. Removing includes: - CREATE TABLE and ALTER TABLE syntax for declaring the table to be WITH OIDS has been removed (WITH (oids[ = true]) will error out) - pg_dump does not support dumping tables declared WITH OIDS and will issue a warning when dumping one (and ignore the oid column). - restoring an pg_dump archive with pg_restore will warn when restoring a table with oid contents (and ignore the oid column) - COPY will refuse to load binary dump that includes oids. - pg_upgrade will error out when encountering tables declared WITH OIDS, they have to be altered to remove the oid column first. - Functionality to access the oid of the last inserted row (like plpgsql's RESULT_OID, spi's SPI_lastoid, ...) has been removed. The syntax for declaring a table WITHOUT OIDS (or WITH (oids = false) for CREATE TABLE) is still supported. While that requires a bit of support code, it seems unnecessary to break applications / dumps that do not use oids, and are explicit about not using them. The biggest user of WITH OID columns was postgres' catalog. This commit changes all 'magic' oid columns to be columns that are normally declared and stored. To reduce unnecessary query breakage all the newly added columns are still named 'oid', even if a table's column naming scheme would indicate 'reloid' or such. This obviously requires adapting a lot code, mostly replacing oid access via HeapTupleGetOid() with access to the underlying Form_pg_*->oid column. The bootstrap process now assigns oids for all oid columns in genbki.pl that do not have an explicit value (starting at the largest oid previously used), only oids assigned later by oids will be above FirstBootstrapObjectId. As the oid column now is a normal column the special bootstrap syntax for oids has been removed. Oids are not automatically assigned during insertion anymore, all backend code explicitly assigns oids with GetNewOidWithIndex(). For the rare case that insertions into the catalog via SQL are called for the new pg_nextoid() function can be used (which only works on catalog tables). The fact that oid columns on system tables are now normal columns means that they will be included in the set of columns expanded by * (i.e. SELECT * FROM pg_class will now include the table's oid, previously it did not). It'd not technically be hard to hide oid column by default, but that'd mean confusing behavior would either have to be carried forward forever, or it'd cause breakage down the line. While it's not unlikely that further adjustments are needed, the scope/invasiveness of the patch makes it worthwhile to get merge this now. It's painful to maintain externally, too complicated to commit after the code code freeze, and a dependency of a number of other patches. Catversion bump, for obvious reasons. Author: Andres Freund, with contributions by John Naylor Discussion: https://postgr.es/m/20180930034810.ywp2c7awz7opzcfr@alap3.anarazel.de
2018-11-21 00:36:57 +01:00
oid = GetSysCacheOid1(PUBLICATIONNAME, Anum_pg_publication_oid,
CStringGetDatum(pubname));
if (!OidIsValid(oid) && !missing_ok)
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_OBJECT),
errmsg("publication \"%s\" does not exist", pubname)));
return oid;
}
/*
* get_publication_name - given a publication Oid, look up the name
*
* If missing_ok is false, throw an error if name not found. If true, just
* return NULL.
*/
char *
get_publication_name(Oid pubid, bool missing_ok)
{
HeapTuple tup;
char *pubname;
Form_pg_publication pubform;
tup = SearchSysCache1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
if (!HeapTupleIsValid(tup))
{
if (!missing_ok)
elog(ERROR, "cache lookup failed for publication %u", pubid);
return NULL;
}
pubform = (Form_pg_publication) GETSTRUCT(tup);
pubname = pstrdup(NameStr(pubform->pubname));
ReleaseSysCache(tup);
return pubname;
}
/*
* Returns Oids of tables in a publication.
*/
Datum
pg_get_publication_tables(PG_FUNCTION_ARGS)
{
FuncCallContext *funcctx;
char *pubname = text_to_cstring(PG_GETARG_TEXT_PP(0));
Publication *publication;
List *tables;
ListCell **lcp;
/* stuff done only on the first call of the function */
if (SRF_IS_FIRSTCALL())
{
MemoryContext oldcontext;
/* create a function context for cross-call persistence */
funcctx = SRF_FIRSTCALL_INIT();
/* switch to memory context appropriate for multiple function calls */
oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
publication = GetPublicationByName(pubname, false);
if (publication->alltables)
tables = GetAllTablesPublicationRelations();
else
tables = GetPublicationRelations(publication->oid);
lcp = (ListCell **) palloc(sizeof(ListCell *));
*lcp = list_head(tables);
funcctx->user_fctx = (void *) lcp;
MemoryContextSwitchTo(oldcontext);
}
/* stuff done on every call of the function */
funcctx = SRF_PERCALL_SETUP();
lcp = (ListCell **) funcctx->user_fctx;
while (*lcp != NULL)
{
Oid relid = lfirst_oid(*lcp);
*lcp = lnext(*lcp);
SRF_RETURN_NEXT(funcctx, ObjectIdGetDatum(relid));
}
SRF_RETURN_DONE(funcctx);
}