postgresql/src/backend/executor/execJunk.c

319 lines
8 KiB
C
Raw Normal View History

/*-------------------------------------------------------------------------
*
* execJunk.c
* Junk attribute support stuff....
*
* Portions Copyright (c) 1996-2019, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
2010-09-20 16:08:53 -04:00
* src/backend/executor/execJunk.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "executor/executor.h"
/*-------------------------------------------------------------------------
* XXX this stuff should be rewritten to take advantage
* of ExecProject() and the ProjectionInfo node.
* -cim 6/3/91
*
* An attribute of a tuple living inside the executor, can be
* either a normal attribute or a "junk" attribute. "junk" attributes
* never make it out of the executor, i.e. they are never printed,
2004-10-10 22:02:41 -04:00
* returned or stored on disk. Their only purpose in life is to
* store some information useful only to the executor, mainly the values
* of system attributes like "ctid", or sort key columns that are not to
* be output.
*
* The general idea is the following: A target list consists of a list of
* TargetEntry nodes containing expressions. Each TargetEntry has a field
* called 'resjunk'. If the value of this field is true then the
* corresponding attribute is a "junk" attribute.
*
* When we initialize a plan we call ExecInitJunkFilter to create a filter.
*
* We then execute the plan, treating the resjunk attributes like any others.
*
* Finally, when at the top level we get back a tuple, we can call
* ExecFindJunkAttribute/ExecGetJunkAttribute to retrieve the values of the
* junk attributes we are interested in, and ExecFilterJunk to remove all the
* junk attributes from a tuple. This new "clean" tuple is then printed,
* inserted, or updated.
*
*-------------------------------------------------------------------------
*/
/*
* ExecInitJunkFilter
*
* Initialize the Junk filter.
*
* The source targetlist is passed in. The output tuple descriptor is
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
2018-11-20 18:36:57 -05:00
* built from the non-junk tlist entries.
* An optional resultSlot can be passed as well.
*/
JunkFilter *
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
2018-11-20 18:36:57 -05:00
ExecInitJunkFilter(List *targetList, TupleTableSlot *slot)
{
JunkFilter *junkfilter;
TupleDesc cleanTupType;
int cleanLength;
AttrNumber *cleanMap;
ListCell *t;
AttrNumber cleanResno;
/*
* Compute the tuple descriptor for the cleaned 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
2018-11-20 18:36:57 -05:00
cleanTupType = ExecCleanTypeFromTL(targetList);
/*
* Use the given slot, or make a new slot if we weren't given one.
*/
if (slot)
ExecSetSlotDescriptor(slot, cleanTupType);
else
Introduce notion of different types of slots (without implementing them). Upcoming work intends to allow pluggable ways to introduce new ways of storing table data. Accessing those table access methods from the executor requires TupleTableSlots to be carry tuples in the native format of such storage methods; otherwise there'll be a significant conversion overhead. Different access methods will require different data to store tuples efficiently (just like virtual, minimal, heap already require fields in TupleTableSlot). To allow that without requiring additional pointer indirections, we want to have different structs (embedding TupleTableSlot) for different types of slots. Thus different types of slots are needed, which requires adapting creators of slots. The slot that most efficiently can represent a type of tuple in an executor node will often depend on the type of slot a child node uses. Therefore we need to track the type of slot is returned by nodes, so parent slots can create slots based on that. Relatedly, JIT compilation of tuple deforming needs to know which type of slot a certain expression refers to, so it can create an appropriate deforming function for the type of tuple in the slot. But not all nodes will only return one type of slot, e.g. an append node will potentially return different types of slots for each of its subplans. Therefore add function that allows to query the type of a node's result slot, and whether it'll always be the same type (whether it's fixed). This can be queried using ExecGetResultSlotOps(). The scan, result, inner, outer type of slots are automatically inferred from ExecInitScanTupleSlot(), ExecInitResultSlot(), left/right subtrees respectively. If that's not correct for a node, that can be overwritten using new fields in PlanState. This commit does not introduce the actually abstracted implementation of different kind of TupleTableSlots, that will be left for a followup commit. The different types of slots introduced will, for now, still use the same backing implementation. While this already partially invalidates the big comment in tuptable.h, it seems to make more sense to update it later, when the different TupleTableSlot implementations actually exist. Author: Ashutosh Bapat and Andres Freund, with changes by Amit Khandekar Discussion: https://postgr.es/m/20181105210039.hh4vvi4vwoq5ba2q@alap3.anarazel.de
2018-11-16 01:00:30 -05:00
slot = MakeSingleTupleTableSlot(cleanTupType, &TTSOpsVirtual);
/*
* Now calculate the mapping between the original tuple's attributes and
* the "clean" tuple's attributes.
*
* The "map" is an array of "cleanLength" attribute numbers, i.e. one
* entry for every attribute of the "clean" tuple. The value of this entry
* is the attribute number of the corresponding attribute of the
* "original" tuple. (Zero indicates a NULL output attribute, but we do
* not use that feature in this routine.)
*/
cleanLength = cleanTupType->natts;
if (cleanLength > 0)
{
cleanMap = (AttrNumber *) palloc(cleanLength * sizeof(AttrNumber));
cleanResno = 1;
foreach(t, targetList)
{
TargetEntry *tle = lfirst(t);
if (!tle->resjunk)
{
cleanMap[cleanResno - 1] = tle->resno;
cleanResno++;
}
}
}
else
cleanMap = NULL;
/*
* Finally create and initialize the JunkFilter struct.
*/
junkfilter = makeNode(JunkFilter);
junkfilter->jf_targetList = targetList;
junkfilter->jf_cleanTupType = cleanTupType;
junkfilter->jf_cleanMap = cleanMap;
junkfilter->jf_resultSlot = slot;
return junkfilter;
}
/*
* ExecInitJunkFilterConversion
*
* Initialize a JunkFilter for rowtype conversions.
*
* Here, we are given the target "clean" tuple descriptor rather than
* inferring it from the targetlist. The target descriptor can contain
* deleted columns. It is assumed that the caller has checked that the
* non-deleted columns match up with the non-junk columns of the targetlist.
*/
JunkFilter *
ExecInitJunkFilterConversion(List *targetList,
TupleDesc cleanTupType,
TupleTableSlot *slot)
{
JunkFilter *junkfilter;
int cleanLength;
AttrNumber *cleanMap;
ListCell *t;
int i;
/*
* Use the given slot, or make a new slot if we weren't given one.
*/
if (slot)
ExecSetSlotDescriptor(slot, cleanTupType);
else
Introduce notion of different types of slots (without implementing them). Upcoming work intends to allow pluggable ways to introduce new ways of storing table data. Accessing those table access methods from the executor requires TupleTableSlots to be carry tuples in the native format of such storage methods; otherwise there'll be a significant conversion overhead. Different access methods will require different data to store tuples efficiently (just like virtual, minimal, heap already require fields in TupleTableSlot). To allow that without requiring additional pointer indirections, we want to have different structs (embedding TupleTableSlot) for different types of slots. Thus different types of slots are needed, which requires adapting creators of slots. The slot that most efficiently can represent a type of tuple in an executor node will often depend on the type of slot a child node uses. Therefore we need to track the type of slot is returned by nodes, so parent slots can create slots based on that. Relatedly, JIT compilation of tuple deforming needs to know which type of slot a certain expression refers to, so it can create an appropriate deforming function for the type of tuple in the slot. But not all nodes will only return one type of slot, e.g. an append node will potentially return different types of slots for each of its subplans. Therefore add function that allows to query the type of a node's result slot, and whether it'll always be the same type (whether it's fixed). This can be queried using ExecGetResultSlotOps(). The scan, result, inner, outer type of slots are automatically inferred from ExecInitScanTupleSlot(), ExecInitResultSlot(), left/right subtrees respectively. If that's not correct for a node, that can be overwritten using new fields in PlanState. This commit does not introduce the actually abstracted implementation of different kind of TupleTableSlots, that will be left for a followup commit. The different types of slots introduced will, for now, still use the same backing implementation. While this already partially invalidates the big comment in tuptable.h, it seems to make more sense to update it later, when the different TupleTableSlot implementations actually exist. Author: Ashutosh Bapat and Andres Freund, with changes by Amit Khandekar Discussion: https://postgr.es/m/20181105210039.hh4vvi4vwoq5ba2q@alap3.anarazel.de
2018-11-16 01:00:30 -05:00
slot = MakeSingleTupleTableSlot(cleanTupType, &TTSOpsVirtual);
/*
2005-10-14 22:49:52 -04:00
* Calculate the mapping between the original tuple's attributes and the
* "clean" tuple's attributes.
*
* The "map" is an array of "cleanLength" attribute numbers, i.e. one
* entry for every attribute of the "clean" tuple. The value of this entry
* is the attribute number of the corresponding attribute of the
* "original" tuple. We store zero for any deleted attributes, marking
* that a NULL is needed in the output tuple.
*/
cleanLength = cleanTupType->natts;
if (cleanLength > 0)
{
cleanMap = (AttrNumber *) palloc0(cleanLength * sizeof(AttrNumber));
t = list_head(targetList);
for (i = 0; i < cleanLength; i++)
{
if (TupleDescAttr(cleanTupType, i)->attisdropped)
continue; /* map entry is already zero */
for (;;)
{
TargetEntry *tle = lfirst(t);
t = lnext(t);
if (!tle->resjunk)
{
cleanMap[i] = tle->resno;
break;
}
}
}
}
else
cleanMap = NULL;
/*
* Finally create and initialize the JunkFilter struct.
*/
junkfilter = makeNode(JunkFilter);
junkfilter->jf_targetList = targetList;
junkfilter->jf_cleanTupType = cleanTupType;
junkfilter->jf_cleanMap = cleanMap;
junkfilter->jf_resultSlot = slot;
1998-08-31 23:29:17 -04:00
return junkfilter;
}
/*
* ExecFindJunkAttribute
*
* Locate the specified junk attribute in the junk filter's targetlist,
* and return its resno. Returns InvalidAttrNumber if not found.
*/
AttrNumber
ExecFindJunkAttribute(JunkFilter *junkfilter, const char *attrName)
{
return ExecFindJunkAttributeInTlist(junkfilter->jf_targetList, attrName);
}
/*
* ExecFindJunkAttributeInTlist
*
* Find a junk attribute given a subplan's targetlist (not necessarily
* part of a JunkFilter).
*/
AttrNumber
ExecFindJunkAttributeInTlist(List *targetlist, const char *attrName)
{
ListCell *t;
foreach(t, targetlist)
{
TargetEntry *tle = lfirst(t);
if (tle->resjunk && tle->resname &&
(strcmp(tle->resname, attrName) == 0))
{
/* We found it ! */
return tle->resno;
}
}
return InvalidAttrNumber;
}
/*
* ExecGetJunkAttribute
*
* Given a junk filter's input tuple (slot) and a junk attribute's number
* previously found by ExecFindJunkAttribute, extract & return the value and
* isNull flag of the attribute.
*/
Datum
ExecGetJunkAttribute(TupleTableSlot *slot, AttrNumber attno,
bool *isNull)
{
Assert(attno > 0);
return slot_getattr(slot, attno, isNull);
}
/*
* ExecFilterJunk
*
* Construct and return a slot with all the junk attributes removed.
*/
TupleTableSlot *
ExecFilterJunk(JunkFilter *junkfilter, TupleTableSlot *slot)
{
TupleTableSlot *resultSlot;
AttrNumber *cleanMap;
TupleDesc cleanTupType;
int cleanLength;
int i;
Datum *values;
bool *isnull;
Datum *old_values;
bool *old_isnull;
/*
* Extract all the values of the old tuple.
*/
slot_getallattrs(slot);
old_values = slot->tts_values;
old_isnull = slot->tts_isnull;
/*
* get info from the junk filter
*/
cleanTupType = junkfilter->jf_cleanTupType;
cleanLength = cleanTupType->natts;
cleanMap = junkfilter->jf_cleanMap;
resultSlot = junkfilter->jf_resultSlot;
/*
* Prepare to build a virtual result tuple.
*/
ExecClearTuple(resultSlot);
values = resultSlot->tts_values;
isnull = resultSlot->tts_isnull;
/*
* Transpose data into proper fields of the new tuple.
*/
for (i = 0; i < cleanLength; i++)
{
int j = cleanMap[i];
if (j == 0)
{
values[i] = (Datum) 0;
isnull[i] = true;
}
else
{
values[i] = old_values[j - 1];
isnull[i] = old_isnull[j - 1];
}
}
/*
* And return the virtual tuple.
*/
return ExecStoreVirtualTuple(resultSlot);
}