2011-02-20 06:17:18 +01:00
|
|
|
/*-------------------------------------------------------------------------
|
|
|
|
|
*
|
|
|
|
|
* nodeForeignscan.c
|
|
|
|
|
* Routines to support scans of foreign tables
|
|
|
|
|
*
|
2023-01-02 21:00:37 +01:00
|
|
|
* Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
|
2011-02-20 06:17:18 +01:00
|
|
|
* Portions Copyright (c) 1994, Regents of the University of California
|
|
|
|
|
*
|
|
|
|
|
*
|
|
|
|
|
* IDENTIFICATION
|
|
|
|
|
* src/backend/executor/nodeForeignscan.c
|
|
|
|
|
*
|
|
|
|
|
*-------------------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
/*
|
|
|
|
|
* INTERFACE ROUTINES
|
|
|
|
|
*
|
|
|
|
|
* ExecForeignScan scans a foreign table.
|
|
|
|
|
* ExecInitForeignScan creates and initializes state info.
|
|
|
|
|
* ExecReScanForeignScan rescans the foreign relation.
|
|
|
|
|
* ExecEndForeignScan releases any resources allocated.
|
|
|
|
|
*/
|
|
|
|
|
#include "postgres.h"
|
|
|
|
|
|
|
|
|
|
#include "executor/executor.h"
|
|
|
|
|
#include "executor/nodeForeignscan.h"
|
|
|
|
|
#include "foreign/fdwapi.h"
|
2015-10-15 19:00:40 +02:00
|
|
|
#include "utils/memutils.h"
|
2011-02-23 18:18:09 +01:00
|
|
|
#include "utils/rel.h"
|
2011-02-20 06:17:18 +01:00
|
|
|
|
|
|
|
|
static TupleTableSlot *ForeignNext(ForeignScanState *node);
|
|
|
|
|
static bool ForeignRecheck(ForeignScanState *node, TupleTableSlot *slot);
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
|
* ForeignNext
|
|
|
|
|
*
|
|
|
|
|
* This is a workhorse for ExecForeignScan
|
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
static TupleTableSlot *
|
|
|
|
|
ForeignNext(ForeignScanState *node)
|
|
|
|
|
{
|
|
|
|
|
TupleTableSlot *slot;
|
|
|
|
|
ForeignScan *plan = (ForeignScan *) node->ss.ps.plan;
|
|
|
|
|
ExprContext *econtext = node->ss.ps.ps_ExprContext;
|
|
|
|
|
MemoryContext oldcontext;
|
|
|
|
|
|
|
|
|
|
/* Call the Iterate function in short-lived context */
|
|
|
|
|
oldcontext = MemoryContextSwitchTo(econtext->ecxt_per_tuple_memory);
|
2016-03-18 18:48:58 +01:00
|
|
|
if (plan->operation != CMD_SELECT)
|
2021-08-12 10:02:29 +02:00
|
|
|
{
|
|
|
|
|
/*
|
|
|
|
|
* direct modifications cannot be re-evaluated, so shouldn't get here
|
|
|
|
|
* during EvalPlanQual processing
|
|
|
|
|
*/
|
2022-02-03 19:44:26 +01:00
|
|
|
Assert(node->ss.ps.state->es_epq_active == NULL);
|
2021-08-12 10:02:29 +02:00
|
|
|
|
2016-03-18 18:48:58 +01:00
|
|
|
slot = node->fdwroutine->IterateDirectModify(node);
|
2021-08-12 10:02:29 +02:00
|
|
|
}
|
2016-03-18 18:48:58 +01:00
|
|
|
else
|
|
|
|
|
slot = node->fdwroutine->IterateForeignScan(node);
|
2011-02-20 06:17:18 +01:00
|
|
|
MemoryContextSwitchTo(oldcontext);
|
|
|
|
|
|
|
|
|
|
/*
|
Store table oid and tuple's tid in tuple slots directly.
After the introduction of tuple table slots all table AMs need to
support returning the table oid of the tuple stored in a slot created
by said AM. It does not make sense to re-implement that in every AM,
therefore move handling of table OIDs into the TupleTableSlot
structure itself. It's possible that we, at a later date, might want
to get rid of HeapTupleData.t_tableOid entirely, but doing so before
the abstractions for table AMs are integrated turns out to be too
hard, so delay that for now.
Similarly, every AM needs to support the concept of a tuple
identifier (tid / item pointer) for its tuples. It's quite possible
that we'll generalize the exact form of a tid at a future point (to
allow for things like index organized tables), but for now many parts
of the code know about tids, so there's not much point in abstracting
tids away. Therefore also move into slot (rather than providing API to
set/get the tid associated with the tuple in a slot).
Once table AM includes insert/updating/deleting tuples, the
responsibility to set the correct tid after such an action will move
into that. After that change, code doing such modifications, should
not have to deal with HeapTuples directly anymore.
Author: Andres Freund, Haribabu Kommi and Ashutosh Bapat
Discussion: https://postgr.es/m/20180703070645.wchpu5muyto5n647@alap3.anarazel.de
2019-02-27 03:21:44 +01:00
|
|
|
* Insert valid value into tableoid, the only actually-useful system
|
|
|
|
|
* column.
|
2011-02-20 06:17:18 +01:00
|
|
|
*/
|
|
|
|
|
if (plan->fsSystemCol && !TupIsNull(slot))
|
Store table oid and tuple's tid in tuple slots directly.
After the introduction of tuple table slots all table AMs need to
support returning the table oid of the tuple stored in a slot created
by said AM. It does not make sense to re-implement that in every AM,
therefore move handling of table OIDs into the TupleTableSlot
structure itself. It's possible that we, at a later date, might want
to get rid of HeapTupleData.t_tableOid entirely, but doing so before
the abstractions for table AMs are integrated turns out to be too
hard, so delay that for now.
Similarly, every AM needs to support the concept of a tuple
identifier (tid / item pointer) for its tuples. It's quite possible
that we'll generalize the exact form of a tid at a future point (to
allow for things like index organized tables), but for now many parts
of the code know about tids, so there's not much point in abstracting
tids away. Therefore also move into slot (rather than providing API to
set/get the tid associated with the tuple in a slot).
Once table AM includes insert/updating/deleting tuples, the
responsibility to set the correct tid after such an action will move
into that. After that change, code doing such modifications, should
not have to deal with HeapTuples directly anymore.
Author: Andres Freund, Haribabu Kommi and Ashutosh Bapat
Discussion: https://postgr.es/m/20180703070645.wchpu5muyto5n647@alap3.anarazel.de
2019-02-27 03:21:44 +01:00
|
|
|
slot->tts_tableOid = RelationGetRelid(node->ss.ss_currentRelation);
|
2011-02-20 06:17:18 +01:00
|
|
|
|
|
|
|
|
return slot;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* ForeignRecheck -- access method routine to recheck a tuple in EvalPlanQual
|
|
|
|
|
*/
|
|
|
|
|
static bool
|
|
|
|
|
ForeignRecheck(ForeignScanState *node, TupleTableSlot *slot)
|
|
|
|
|
{
|
Allow foreign and custom joins to handle EvalPlanQual rechecks.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 provided basic
infrastructure for allowing a foreign data wrapper or custom scan
provider to replace a join of one or more tables with a scan.
However, this infrastructure failed to take into account the need
for possible EvalPlanQual rechecks, and ExecScanFetch would fail
an assertion (or just overwrite memory) if such a check was attempted
for a plan containing a pushed-down join. To fix, adjust the EPQ
machinery to skip some processing steps when scanrelid == 0, making
those the responsibility of scan's recheck method, which also has
the responsibility in this case of correctly populating the relevant
slot.
To allow foreign scans to gain control in the right place to make
use of this new facility, add a new, optional RecheckForeignScan
method. Also, allow a foreign scan to have a child plan, which can
be used to correctly populate the slot (or perhaps for something
else, but this is the only use currently envisioned).
KaiGai Kohei, reviewed by Robert Haas, Etsuro Fujita, and Kyotaro
Horiguchi.
2015-12-08 18:31:03 +01:00
|
|
|
FdwRoutine *fdwroutine = node->fdwroutine;
|
2015-10-15 19:00:40 +02:00
|
|
|
ExprContext *econtext;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* extract necessary information from foreign scan node
|
|
|
|
|
*/
|
|
|
|
|
econtext = node->ss.ps.ps_ExprContext;
|
|
|
|
|
|
|
|
|
|
/* Does the tuple meet the remote qual condition? */
|
|
|
|
|
econtext->ecxt_scantuple = slot;
|
|
|
|
|
|
|
|
|
|
ResetExprContext(econtext);
|
|
|
|
|
|
Allow foreign and custom joins to handle EvalPlanQual rechecks.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 provided basic
infrastructure for allowing a foreign data wrapper or custom scan
provider to replace a join of one or more tables with a scan.
However, this infrastructure failed to take into account the need
for possible EvalPlanQual rechecks, and ExecScanFetch would fail
an assertion (or just overwrite memory) if such a check was attempted
for a plan containing a pushed-down join. To fix, adjust the EPQ
machinery to skip some processing steps when scanrelid == 0, making
those the responsibility of scan's recheck method, which also has
the responsibility in this case of correctly populating the relevant
slot.
To allow foreign scans to gain control in the right place to make
use of this new facility, add a new, optional RecheckForeignScan
method. Also, allow a foreign scan to have a child plan, which can
be used to correctly populate the slot (or perhaps for something
else, but this is the only use currently envisioned).
KaiGai Kohei, reviewed by Robert Haas, Etsuro Fujita, and Kyotaro
Horiguchi.
2015-12-08 18:31:03 +01:00
|
|
|
/*
|
|
|
|
|
* If an outer join is pushed down, RecheckForeignScan may need to store a
|
|
|
|
|
* different tuple in the slot, because a different set of columns may go
|
|
|
|
|
* to NULL upon recheck. Otherwise, it shouldn't need to change the slot
|
|
|
|
|
* contents, just return true or false to indicate whether the quals still
|
|
|
|
|
* pass. For simple cases, setting fdw_recheck_quals may be easier than
|
|
|
|
|
* providing this callback.
|
|
|
|
|
*/
|
|
|
|
|
if (fdwroutine->RecheckForeignScan &&
|
|
|
|
|
!fdwroutine->RecheckForeignScan(node, slot))
|
|
|
|
|
return false;
|
|
|
|
|
|
Faster expression evaluation and targetlist projection.
This replaces the old, recursive tree-walk based evaluation, with
non-recursive, opcode dispatch based, expression evaluation.
Projection is now implemented as part of expression evaluation.
This both leads to significant performance improvements, and makes
future just-in-time compilation of expressions easier.
The speed gains primarily come from:
- non-recursive implementation reduces stack usage / overhead
- simple sub-expressions are implemented with a single jump, without
function calls
- sharing some state between different sub-expressions
- reduced amount of indirect/hard to predict memory accesses by laying
out operation metadata sequentially; including the avoidance of
nearly all of the previously used linked lists
- more code has been moved to expression initialization, avoiding
constant re-checks at evaluation time
Future just-in-time compilation (JIT) has become easier, as
demonstrated by released patches intended to be merged in a later
release, for primarily two reasons: Firstly, due to a stricter split
between expression initialization and evaluation, less code has to be
handled by the JIT. Secondly, due to the non-recursive nature of the
generated "instructions", less performance-critical code-paths can
easily be shared between interpreted and compiled evaluation.
The new framework allows for significant future optimizations. E.g.:
- basic infrastructure for to later reduce the per executor-startup
overhead of expression evaluation, by caching state in prepared
statements. That'd be helpful in OLTPish scenarios where
initialization overhead is measurable.
- optimizing the generated "code". A number of proposals for potential
work has already been made.
- optimizing the interpreter. Similarly a number of proposals have
been made here too.
The move of logic into the expression initialization step leads to some
backward-incompatible changes:
- Function permission checks are now done during expression
initialization, whereas previously they were done during
execution. In edge cases this can lead to errors being raised that
previously wouldn't have been, e.g. a NULL array being coerced to a
different array type previously didn't perform checks.
- The set of domain constraints to be checked, is now evaluated once
during expression initialization, previously it was re-built
every time a domain check was evaluated. For normal queries this
doesn't change much, but e.g. for plpgsql functions, which caches
ExprStates, the old set could stick around longer. The behavior
around might still change.
Author: Andres Freund, with significant changes by Tom Lane,
changes by Heikki Linnakangas
Reviewed-By: Tom Lane, Heikki Linnakangas
Discussion: https://postgr.es/m/20161206034955.bh33paeralxbtluv@alap3.anarazel.de
2017-03-14 23:45:36 +01:00
|
|
|
return ExecQual(node->fdw_recheck_quals, econtext);
|
2011-02-20 06:17:18 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
|
* ExecForeignScan(node)
|
|
|
|
|
*
|
|
|
|
|
* Fetches the next tuple from the FDW, checks local quals, and
|
|
|
|
|
* returns it.
|
|
|
|
|
* We call the ExecScan() routine and pass it the appropriate
|
|
|
|
|
* access method functions.
|
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
|
*/
|
2017-07-17 09:33:49 +02:00
|
|
|
static TupleTableSlot *
|
|
|
|
|
ExecForeignScan(PlanState *pstate)
|
2011-02-20 06:17:18 +01:00
|
|
|
{
|
2017-07-17 09:33:49 +02:00
|
|
|
ForeignScanState *node = castNode(ForeignScanState, pstate);
|
2022-02-03 07:15:00 +01:00
|
|
|
ForeignScan *plan = (ForeignScan *) node->ss.ps.plan;
|
|
|
|
|
EState *estate = node->ss.ps.state;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Ignore direct modifications when EvalPlanQual is active --- they are
|
|
|
|
|
* irrelevant for EvalPlanQual rechecking
|
|
|
|
|
*/
|
|
|
|
|
if (estate->es_epq_active != NULL && plan->operation != CMD_SELECT)
|
|
|
|
|
return NULL;
|
2017-07-17 09:33:49 +02:00
|
|
|
|
|
|
|
|
return ExecScan(&node->ss,
|
2011-02-20 06:17:18 +01:00
|
|
|
(ExecScanAccessMtd) ForeignNext,
|
|
|
|
|
(ExecScanRecheckMtd) ForeignRecheck);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
|
* ExecInitForeignScan
|
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
ForeignScanState *
|
|
|
|
|
ExecInitForeignScan(ForeignScan *node, EState *estate, int eflags)
|
|
|
|
|
{
|
|
|
|
|
ForeignScanState *scanstate;
|
Code review for foreign/custom join pushdown patch.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 included some design
decisions that seem pretty questionable to me, and there was quite a lot
of stuff not to like about the documentation and comments. Clean up
as follows:
* Consider foreign joins only between foreign tables on the same server,
rather than between any two foreign tables with the same underlying FDW
handler function. In most if not all cases, the FDW would simply have had
to apply the same-server restriction itself (far more expensively, both for
lack of caching and because it would be repeated for each combination of
input sub-joins), or else risk nasty bugs. Anyone who's really intent on
doing something outside this restriction can always use the
set_join_pathlist_hook.
* Rename fdw_ps_tlist/custom_ps_tlist to fdw_scan_tlist/custom_scan_tlist
to better reflect what they're for, and allow these custom scan tlists
to be used even for base relations.
* Change make_foreignscan() API to include passing the fdw_scan_tlist
value, since the FDW is required to set that. Backwards compatibility
doesn't seem like an adequate reason to expect FDWs to set it in some
ad-hoc extra step, and anyway existing FDWs can just pass NIL.
* Change the API of path-generating subroutines of add_paths_to_joinrel,
and in particular that of GetForeignJoinPaths and set_join_pathlist_hook,
so that various less-used parameters are passed in a struct rather than
as separate parameter-list entries. The objective here is to reduce the
probability that future additions to those parameter lists will result in
source-level API breaks for users of these hooks. It's possible that this
is even a small win for the core code, since most CPU architectures can't
pass more than half a dozen parameters efficiently anyway. I kept root,
joinrel, outerrel, innerrel, and jointype as separate parameters to reduce
code churn in joinpath.c --- in particular, putting jointype into the
struct would have been problematic because of the subroutines' habit of
changing their local copies of that variable.
* Avoid ad-hocery in ExecAssignScanProjectionInfo. It was probably all
right for it to know about IndexOnlyScan, but if the list is to grow
we should refactor the knowledge out to the callers.
* Restore nodeForeignscan.c's previous use of the relcache to avoid
extra GetFdwRoutine lookups for base-relation scans.
* Lots of cleanup of documentation and missed comments. Re-order some
code additions into more logical places.
2015-05-10 20:36:30 +02:00
|
|
|
Relation currentRelation = NULL;
|
2015-05-01 14:50:35 +02:00
|
|
|
Index scanrelid = node->scan.scanrelid;
|
Remove arbitrary 64K-or-so limit on rangetable size.
Up to now the size of a query's rangetable has been limited by the
constants INNER_VAR et al, which mustn't be equal to any real
rangetable index. 65000 doubtless seemed like enough for anybody,
and it still is orders of magnitude larger than the number of joins
we can realistically handle. However, we need a rangetable entry
for each child partition that is (or might be) processed by a query.
Queries with a few thousand partitions are getting more realistic,
so that the day when that limit becomes a problem is in sight,
even if it's not here yet. Hence, let's raise the limit.
Rather than just increase the values of INNER_VAR et al, this patch
adopts the approach of making them small negative values, so that
rangetables could theoretically become as long as INT_MAX.
The bulk of the patch is concerned with changing Var.varno and some
related variables from "Index" (unsigned int) to plain "int". This
is basically cosmetic, with little actual effect other than to help
debuggers print their values nicely. As such, I've only bothered
with changing places that could actually see INNER_VAR et al, which
the parser and most of the planner don't. We do have to be careful
in places that are performing less/greater comparisons on varnos,
but there are very few such places, other than the IS_SPECIAL_VARNO
macro itself.
A notable side effect of this patch is that while it used to be
possible to add INNER_VAR et al to a Bitmapset, that will now
draw an error. I don't see any likelihood that it wouldn't be a
bug to include these fake varnos in a bitmapset of real varnos,
so I think this is all to the good.
Although this touches outfuncs/readfuncs, I don't think a catversion
bump is required, since stored rules would never contain Vars
with these fake varnos.
Andrey Lepikhov and Tom Lane, after a suggestion by Peter Eisentraut
Discussion: https://postgr.es/m/43c7f2f5-1e27-27aa-8c65-c91859d15190@postgrespro.ru
2021-09-15 20:11:21 +02:00
|
|
|
int tlistvarno;
|
2011-02-20 06:17:18 +01:00
|
|
|
FdwRoutine *fdwroutine;
|
|
|
|
|
|
|
|
|
|
/* check for unsupported flags */
|
|
|
|
|
Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* create state structure
|
|
|
|
|
*/
|
|
|
|
|
scanstate = makeNode(ForeignScanState);
|
|
|
|
|
scanstate->ss.ps.plan = (Plan *) node;
|
|
|
|
|
scanstate->ss.ps.state = estate;
|
2017-07-17 09:33:49 +02:00
|
|
|
scanstate->ss.ps.ExecProcNode = ExecForeignScan;
|
2011-02-20 06:17:18 +01:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Miscellaneous initialization
|
|
|
|
|
*
|
|
|
|
|
* create expression context for node
|
|
|
|
|
*/
|
|
|
|
|
ExecAssignExprContext(estate, &scanstate->ss.ps);
|
|
|
|
|
|
|
|
|
|
/*
|
2018-10-06 21:49:37 +02:00
|
|
|
* open the scan relation, if any; also acquire function pointers from the
|
|
|
|
|
* FDW's handler
|
2011-02-20 06:17:18 +01:00
|
|
|
*/
|
2015-05-01 14:50:35 +02:00
|
|
|
if (scanrelid > 0)
|
|
|
|
|
{
|
|
|
|
|
currentRelation = ExecOpenScanRelation(estate, scanrelid, eflags);
|
|
|
|
|
scanstate->ss.ss_currentRelation = currentRelation;
|
Code review for foreign/custom join pushdown patch.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 included some design
decisions that seem pretty questionable to me, and there was quite a lot
of stuff not to like about the documentation and comments. Clean up
as follows:
* Consider foreign joins only between foreign tables on the same server,
rather than between any two foreign tables with the same underlying FDW
handler function. In most if not all cases, the FDW would simply have had
to apply the same-server restriction itself (far more expensively, both for
lack of caching and because it would be repeated for each combination of
input sub-joins), or else risk nasty bugs. Anyone who's really intent on
doing something outside this restriction can always use the
set_join_pathlist_hook.
* Rename fdw_ps_tlist/custom_ps_tlist to fdw_scan_tlist/custom_scan_tlist
to better reflect what they're for, and allow these custom scan tlists
to be used even for base relations.
* Change make_foreignscan() API to include passing the fdw_scan_tlist
value, since the FDW is required to set that. Backwards compatibility
doesn't seem like an adequate reason to expect FDWs to set it in some
ad-hoc extra step, and anyway existing FDWs can just pass NIL.
* Change the API of path-generating subroutines of add_paths_to_joinrel,
and in particular that of GetForeignJoinPaths and set_join_pathlist_hook,
so that various less-used parameters are passed in a struct rather than
as separate parameter-list entries. The objective here is to reduce the
probability that future additions to those parameter lists will result in
source-level API breaks for users of these hooks. It's possible that this
is even a small win for the core code, since most CPU architectures can't
pass more than half a dozen parameters efficiently anyway. I kept root,
joinrel, outerrel, innerrel, and jointype as separate parameters to reduce
code churn in joinpath.c --- in particular, putting jointype into the
struct would have been problematic because of the subroutines' habit of
changing their local copies of that variable.
* Avoid ad-hocery in ExecAssignScanProjectionInfo. It was probably all
right for it to know about IndexOnlyScan, but if the list is to grow
we should refactor the knowledge out to the callers.
* Restore nodeForeignscan.c's previous use of the relcache to avoid
extra GetFdwRoutine lookups for base-relation scans.
* Lots of cleanup of documentation and missed comments. Re-order some
code additions into more logical places.
2015-05-10 20:36:30 +02:00
|
|
|
fdwroutine = GetFdwRoutineForRelation(currentRelation, true);
|
2015-05-01 14:50:35 +02:00
|
|
|
}
|
|
|
|
|
else
|
|
|
|
|
{
|
Code review for foreign/custom join pushdown patch.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 included some design
decisions that seem pretty questionable to me, and there was quite a lot
of stuff not to like about the documentation and comments. Clean up
as follows:
* Consider foreign joins only between foreign tables on the same server,
rather than between any two foreign tables with the same underlying FDW
handler function. In most if not all cases, the FDW would simply have had
to apply the same-server restriction itself (far more expensively, both for
lack of caching and because it would be repeated for each combination of
input sub-joins), or else risk nasty bugs. Anyone who's really intent on
doing something outside this restriction can always use the
set_join_pathlist_hook.
* Rename fdw_ps_tlist/custom_ps_tlist to fdw_scan_tlist/custom_scan_tlist
to better reflect what they're for, and allow these custom scan tlists
to be used even for base relations.
* Change make_foreignscan() API to include passing the fdw_scan_tlist
value, since the FDW is required to set that. Backwards compatibility
doesn't seem like an adequate reason to expect FDWs to set it in some
ad-hoc extra step, and anyway existing FDWs can just pass NIL.
* Change the API of path-generating subroutines of add_paths_to_joinrel,
and in particular that of GetForeignJoinPaths and set_join_pathlist_hook,
so that various less-used parameters are passed in a struct rather than
as separate parameter-list entries. The objective here is to reduce the
probability that future additions to those parameter lists will result in
source-level API breaks for users of these hooks. It's possible that this
is even a small win for the core code, since most CPU architectures can't
pass more than half a dozen parameters efficiently anyway. I kept root,
joinrel, outerrel, innerrel, and jointype as separate parameters to reduce
code churn in joinpath.c --- in particular, putting jointype into the
struct would have been problematic because of the subroutines' habit of
changing their local copies of that variable.
* Avoid ad-hocery in ExecAssignScanProjectionInfo. It was probably all
right for it to know about IndexOnlyScan, but if the list is to grow
we should refactor the knowledge out to the callers.
* Restore nodeForeignscan.c's previous use of the relcache to avoid
extra GetFdwRoutine lookups for base-relation scans.
* Lots of cleanup of documentation and missed comments. Re-order some
code additions into more logical places.
2015-05-10 20:36:30 +02:00
|
|
|
/* We can't use the relcache, so get fdwroutine the hard way */
|
|
|
|
|
fdwroutine = GetFdwRoutineByServerId(node->fs_server);
|
|
|
|
|
}
|
2015-05-01 14:50:35 +02:00
|
|
|
|
Code review for foreign/custom join pushdown patch.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 included some design
decisions that seem pretty questionable to me, and there was quite a lot
of stuff not to like about the documentation and comments. Clean up
as follows:
* Consider foreign joins only between foreign tables on the same server,
rather than between any two foreign tables with the same underlying FDW
handler function. In most if not all cases, the FDW would simply have had
to apply the same-server restriction itself (far more expensively, both for
lack of caching and because it would be repeated for each combination of
input sub-joins), or else risk nasty bugs. Anyone who's really intent on
doing something outside this restriction can always use the
set_join_pathlist_hook.
* Rename fdw_ps_tlist/custom_ps_tlist to fdw_scan_tlist/custom_scan_tlist
to better reflect what they're for, and allow these custom scan tlists
to be used even for base relations.
* Change make_foreignscan() API to include passing the fdw_scan_tlist
value, since the FDW is required to set that. Backwards compatibility
doesn't seem like an adequate reason to expect FDWs to set it in some
ad-hoc extra step, and anyway existing FDWs can just pass NIL.
* Change the API of path-generating subroutines of add_paths_to_joinrel,
and in particular that of GetForeignJoinPaths and set_join_pathlist_hook,
so that various less-used parameters are passed in a struct rather than
as separate parameter-list entries. The objective here is to reduce the
probability that future additions to those parameter lists will result in
source-level API breaks for users of these hooks. It's possible that this
is even a small win for the core code, since most CPU architectures can't
pass more than half a dozen parameters efficiently anyway. I kept root,
joinrel, outerrel, innerrel, and jointype as separate parameters to reduce
code churn in joinpath.c --- in particular, putting jointype into the
struct would have been problematic because of the subroutines' habit of
changing their local copies of that variable.
* Avoid ad-hocery in ExecAssignScanProjectionInfo. It was probably all
right for it to know about IndexOnlyScan, but if the list is to grow
we should refactor the knowledge out to the callers.
* Restore nodeForeignscan.c's previous use of the relcache to avoid
extra GetFdwRoutine lookups for base-relation scans.
* Lots of cleanup of documentation and missed comments. Re-order some
code additions into more logical places.
2015-05-10 20:36:30 +02:00
|
|
|
/*
|
|
|
|
|
* Determine the scan tuple type. If the FDW provided a targetlist
|
|
|
|
|
* describing the scan tuples, use that; else use base relation's rowtype.
|
|
|
|
|
*/
|
|
|
|
|
if (node->fdw_scan_tlist != NIL || currentRelation == NULL)
|
|
|
|
|
{
|
|
|
|
|
TupleDesc scan_tupdesc;
|
|
|
|
|
|
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
|
|
|
scan_tupdesc = ExecTypeFromTL(node->fdw_scan_tlist);
|
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 07:00:30 +01:00
|
|
|
ExecInitScanTupleSlot(estate, &scanstate->ss, scan_tupdesc,
|
|
|
|
|
&TTSOpsHeapTuple);
|
Code review for foreign/custom join pushdown patch.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 included some design
decisions that seem pretty questionable to me, and there was quite a lot
of stuff not to like about the documentation and comments. Clean up
as follows:
* Consider foreign joins only between foreign tables on the same server,
rather than between any two foreign tables with the same underlying FDW
handler function. In most if not all cases, the FDW would simply have had
to apply the same-server restriction itself (far more expensively, both for
lack of caching and because it would be repeated for each combination of
input sub-joins), or else risk nasty bugs. Anyone who's really intent on
doing something outside this restriction can always use the
set_join_pathlist_hook.
* Rename fdw_ps_tlist/custom_ps_tlist to fdw_scan_tlist/custom_scan_tlist
to better reflect what they're for, and allow these custom scan tlists
to be used even for base relations.
* Change make_foreignscan() API to include passing the fdw_scan_tlist
value, since the FDW is required to set that. Backwards compatibility
doesn't seem like an adequate reason to expect FDWs to set it in some
ad-hoc extra step, and anyway existing FDWs can just pass NIL.
* Change the API of path-generating subroutines of add_paths_to_joinrel,
and in particular that of GetForeignJoinPaths and set_join_pathlist_hook,
so that various less-used parameters are passed in a struct rather than
as separate parameter-list entries. The objective here is to reduce the
probability that future additions to those parameter lists will result in
source-level API breaks for users of these hooks. It's possible that this
is even a small win for the core code, since most CPU architectures can't
pass more than half a dozen parameters efficiently anyway. I kept root,
joinrel, outerrel, innerrel, and jointype as separate parameters to reduce
code churn in joinpath.c --- in particular, putting jointype into the
struct would have been problematic because of the subroutines' habit of
changing their local copies of that variable.
* Avoid ad-hocery in ExecAssignScanProjectionInfo. It was probably all
right for it to know about IndexOnlyScan, but if the list is to grow
we should refactor the knowledge out to the callers.
* Restore nodeForeignscan.c's previous use of the relcache to avoid
extra GetFdwRoutine lookups for base-relation scans.
* Lots of cleanup of documentation and missed comments. Re-order some
code additions into more logical places.
2015-05-10 20:36:30 +02:00
|
|
|
/* Node's targetlist will contain Vars with varno = INDEX_VAR */
|
|
|
|
|
tlistvarno = INDEX_VAR;
|
|
|
|
|
}
|
|
|
|
|
else
|
|
|
|
|
{
|
2018-03-26 21:57:19 +02:00
|
|
|
TupleDesc scan_tupdesc;
|
|
|
|
|
|
|
|
|
|
/* don't trust FDWs to return tuples fulfilling NOT NULL constraints */
|
|
|
|
|
scan_tupdesc = CreateTupleDescCopy(RelationGetDescr(currentRelation));
|
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 07:00:30 +01:00
|
|
|
ExecInitScanTupleSlot(estate, &scanstate->ss, scan_tupdesc,
|
|
|
|
|
&TTSOpsHeapTuple);
|
Code review for foreign/custom join pushdown patch.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 included some design
decisions that seem pretty questionable to me, and there was quite a lot
of stuff not to like about the documentation and comments. Clean up
as follows:
* Consider foreign joins only between foreign tables on the same server,
rather than between any two foreign tables with the same underlying FDW
handler function. In most if not all cases, the FDW would simply have had
to apply the same-server restriction itself (far more expensively, both for
lack of caching and because it would be repeated for each combination of
input sub-joins), or else risk nasty bugs. Anyone who's really intent on
doing something outside this restriction can always use the
set_join_pathlist_hook.
* Rename fdw_ps_tlist/custom_ps_tlist to fdw_scan_tlist/custom_scan_tlist
to better reflect what they're for, and allow these custom scan tlists
to be used even for base relations.
* Change make_foreignscan() API to include passing the fdw_scan_tlist
value, since the FDW is required to set that. Backwards compatibility
doesn't seem like an adequate reason to expect FDWs to set it in some
ad-hoc extra step, and anyway existing FDWs can just pass NIL.
* Change the API of path-generating subroutines of add_paths_to_joinrel,
and in particular that of GetForeignJoinPaths and set_join_pathlist_hook,
so that various less-used parameters are passed in a struct rather than
as separate parameter-list entries. The objective here is to reduce the
probability that future additions to those parameter lists will result in
source-level API breaks for users of these hooks. It's possible that this
is even a small win for the core code, since most CPU architectures can't
pass more than half a dozen parameters efficiently anyway. I kept root,
joinrel, outerrel, innerrel, and jointype as separate parameters to reduce
code churn in joinpath.c --- in particular, putting jointype into the
struct would have been problematic because of the subroutines' habit of
changing their local copies of that variable.
* Avoid ad-hocery in ExecAssignScanProjectionInfo. It was probably all
right for it to know about IndexOnlyScan, but if the list is to grow
we should refactor the knowledge out to the callers.
* Restore nodeForeignscan.c's previous use of the relcache to avoid
extra GetFdwRoutine lookups for base-relation scans.
* Lots of cleanup of documentation and missed comments. Re-order some
code additions into more logical places.
2015-05-10 20:36:30 +02:00
|
|
|
/* Node's targetlist will contain Vars with varno = scanrelid */
|
|
|
|
|
tlistvarno = scanrelid;
|
2015-05-01 14:50:35 +02:00
|
|
|
}
|
2011-02-20 06:17:18 +01:00
|
|
|
|
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 07:00:30 +01:00
|
|
|
/* Don't know what an FDW might return */
|
|
|
|
|
scanstate->ss.ps.scanopsfixed = false;
|
|
|
|
|
scanstate->ss.ps.scanopsset = true;
|
|
|
|
|
|
2011-02-20 06:17:18 +01:00
|
|
|
/*
|
2018-02-17 06:17:38 +01:00
|
|
|
* Initialize result slot, type and projection.
|
2011-02-20 06:17:18 +01:00
|
|
|
*/
|
Don't require return slots for nodes without projection.
In a lot of nodes the return slot is not required. That can either be
because the node doesn't do any projection (say an Append node), or
because the node does perform projections but the projection is
optimized away because the projection would yield an identical row.
Slots aren't that small, especially for wide rows, so it's worthwhile
to avoid creating them. It's not possible to just skip creating the
slot - it's currently used to determine the tuple descriptor returned
by ExecGetResultType(). So separate the determination of the result
type from the slot creation. The work previously done internally
ExecInitResultTupleSlotTL() can now also be done separately with
ExecInitResultTypeTL() and ExecInitResultSlot(). That way nodes that
aren't guaranteed to need a result slot, can use
ExecInitResultTypeTL() to determine the result type of the node, and
ExecAssignScanProjectionInfo() (via
ExecConditionalAssignProjectionInfo()) determines that a result slot
is needed, it is created with ExecInitResultSlot().
Besides the advantage of avoiding to create slots that then are
unused, this is necessary preparation for later patches around tuple
table slot abstraction. In particular separating the return descriptor
and slot is a prerequisite to allow JITing of tuple deforming with
knowledge of the underlying tuple format, and to avoid unnecessarily
creating JITed tuple deforming for virtual slots.
This commit removes a redundant argument from
ExecInitResultTupleSlotTL(). While this commit touches a lot of the
relevant lines anyway, it'd normally still not worthwhile to cause
breakage, except that aforementioned later commits will touch *all*
ExecInitResultTupleSlotTL() callers anyway (but fits worse
thematically).
Author: Andres Freund
Discussion: https://postgr.es/m/20181105210039.hh4vvi4vwoq5ba2q@alap3.anarazel.de
2018-11-10 02:19:39 +01:00
|
|
|
ExecInitResultTypeTL(&scanstate->ss.ps);
|
Code review for foreign/custom join pushdown patch.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 included some design
decisions that seem pretty questionable to me, and there was quite a lot
of stuff not to like about the documentation and comments. Clean up
as follows:
* Consider foreign joins only between foreign tables on the same server,
rather than between any two foreign tables with the same underlying FDW
handler function. In most if not all cases, the FDW would simply have had
to apply the same-server restriction itself (far more expensively, both for
lack of caching and because it would be repeated for each combination of
input sub-joins), or else risk nasty bugs. Anyone who's really intent on
doing something outside this restriction can always use the
set_join_pathlist_hook.
* Rename fdw_ps_tlist/custom_ps_tlist to fdw_scan_tlist/custom_scan_tlist
to better reflect what they're for, and allow these custom scan tlists
to be used even for base relations.
* Change make_foreignscan() API to include passing the fdw_scan_tlist
value, since the FDW is required to set that. Backwards compatibility
doesn't seem like an adequate reason to expect FDWs to set it in some
ad-hoc extra step, and anyway existing FDWs can just pass NIL.
* Change the API of path-generating subroutines of add_paths_to_joinrel,
and in particular that of GetForeignJoinPaths and set_join_pathlist_hook,
so that various less-used parameters are passed in a struct rather than
as separate parameter-list entries. The objective here is to reduce the
probability that future additions to those parameter lists will result in
source-level API breaks for users of these hooks. It's possible that this
is even a small win for the core code, since most CPU architectures can't
pass more than half a dozen parameters efficiently anyway. I kept root,
joinrel, outerrel, innerrel, and jointype as separate parameters to reduce
code churn in joinpath.c --- in particular, putting jointype into the
struct would have been problematic because of the subroutines' habit of
changing their local copies of that variable.
* Avoid ad-hocery in ExecAssignScanProjectionInfo. It was probably all
right for it to know about IndexOnlyScan, but if the list is to grow
we should refactor the knowledge out to the callers.
* Restore nodeForeignscan.c's previous use of the relcache to avoid
extra GetFdwRoutine lookups for base-relation scans.
* Lots of cleanup of documentation and missed comments. Re-order some
code additions into more logical places.
2015-05-10 20:36:30 +02:00
|
|
|
ExecAssignScanProjectionInfoWithVarno(&scanstate->ss, tlistvarno);
|
2011-02-20 06:17:18 +01:00
|
|
|
|
2018-02-17 06:17:38 +01:00
|
|
|
/*
|
|
|
|
|
* initialize child expressions
|
|
|
|
|
*/
|
|
|
|
|
scanstate->ss.ps.qual =
|
|
|
|
|
ExecInitQual(node->scan.plan.qual, (PlanState *) scanstate);
|
|
|
|
|
scanstate->fdw_recheck_quals =
|
|
|
|
|
ExecInitQual(node->fdw_recheck_quals, (PlanState *) scanstate);
|
|
|
|
|
|
2021-05-12 07:00:00 +02:00
|
|
|
/*
|
|
|
|
|
* Determine whether to scan the foreign relation asynchronously or not;
|
|
|
|
|
* this has to be kept in sync with the code in ExecInitAppend().
|
|
|
|
|
*/
|
|
|
|
|
scanstate->ss.ps.async_capable = (((Plan *) node)->async_capable &&
|
|
|
|
|
estate->es_epq_active == NULL);
|
|
|
|
|
|
2011-02-20 06:17:18 +01:00
|
|
|
/*
|
Code review for foreign/custom join pushdown patch.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 included some design
decisions that seem pretty questionable to me, and there was quite a lot
of stuff not to like about the documentation and comments. Clean up
as follows:
* Consider foreign joins only between foreign tables on the same server,
rather than between any two foreign tables with the same underlying FDW
handler function. In most if not all cases, the FDW would simply have had
to apply the same-server restriction itself (far more expensively, both for
lack of caching and because it would be repeated for each combination of
input sub-joins), or else risk nasty bugs. Anyone who's really intent on
doing something outside this restriction can always use the
set_join_pathlist_hook.
* Rename fdw_ps_tlist/custom_ps_tlist to fdw_scan_tlist/custom_scan_tlist
to better reflect what they're for, and allow these custom scan tlists
to be used even for base relations.
* Change make_foreignscan() API to include passing the fdw_scan_tlist
value, since the FDW is required to set that. Backwards compatibility
doesn't seem like an adequate reason to expect FDWs to set it in some
ad-hoc extra step, and anyway existing FDWs can just pass NIL.
* Change the API of path-generating subroutines of add_paths_to_joinrel,
and in particular that of GetForeignJoinPaths and set_join_pathlist_hook,
so that various less-used parameters are passed in a struct rather than
as separate parameter-list entries. The objective here is to reduce the
probability that future additions to those parameter lists will result in
source-level API breaks for users of these hooks. It's possible that this
is even a small win for the core code, since most CPU architectures can't
pass more than half a dozen parameters efficiently anyway. I kept root,
joinrel, outerrel, innerrel, and jointype as separate parameters to reduce
code churn in joinpath.c --- in particular, putting jointype into the
struct would have been problematic because of the subroutines' habit of
changing their local copies of that variable.
* Avoid ad-hocery in ExecAssignScanProjectionInfo. It was probably all
right for it to know about IndexOnlyScan, but if the list is to grow
we should refactor the knowledge out to the callers.
* Restore nodeForeignscan.c's previous use of the relcache to avoid
extra GetFdwRoutine lookups for base-relation scans.
* Lots of cleanup of documentation and missed comments. Re-order some
code additions into more logical places.
2015-05-10 20:36:30 +02:00
|
|
|
* Initialize FDW-related state.
|
2011-02-20 06:17:18 +01:00
|
|
|
*/
|
|
|
|
|
scanstate->fdwroutine = fdwroutine;
|
|
|
|
|
scanstate->fdw_state = NULL;
|
|
|
|
|
|
2020-10-14 09:58:38 +02:00
|
|
|
/*
|
2021-08-12 10:02:29 +02:00
|
|
|
* For the FDW's convenience, look up the modification target relation's
|
|
|
|
|
* ResultRelInfo. The ModifyTable node should have initialized it for us,
|
|
|
|
|
* see ExecInitModifyTable.
|
|
|
|
|
*
|
|
|
|
|
* Don't try to look up the ResultRelInfo when EvalPlanQual is active,
|
2022-01-28 07:45:00 +01:00
|
|
|
* though. Direct modifications cannot be re-evaluated as part of
|
2021-08-12 10:02:29 +02:00
|
|
|
* EvalPlanQual. The lookup wouldn't work anyway because during
|
|
|
|
|
* EvalPlanQual processing, EvalPlanQual only initializes the subtree
|
|
|
|
|
* under the ModifyTable, and doesn't run ExecInitModifyTable.
|
2020-10-14 09:58:38 +02:00
|
|
|
*/
|
2021-08-12 10:02:29 +02:00
|
|
|
if (node->resultRelation > 0 && estate->es_epq_active == NULL)
|
|
|
|
|
{
|
|
|
|
|
if (estate->es_result_relations == NULL ||
|
|
|
|
|
estate->es_result_relations[node->resultRelation - 1] == NULL)
|
|
|
|
|
{
|
|
|
|
|
elog(ERROR, "result relation not initialized");
|
|
|
|
|
}
|
2020-10-14 09:58:38 +02:00
|
|
|
scanstate->resultRelInfo = estate->es_result_relations[node->resultRelation - 1];
|
2021-08-12 10:02:29 +02:00
|
|
|
}
|
2020-10-14 09:58:38 +02:00
|
|
|
|
Allow foreign and custom joins to handle EvalPlanQual rechecks.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 provided basic
infrastructure for allowing a foreign data wrapper or custom scan
provider to replace a join of one or more tables with a scan.
However, this infrastructure failed to take into account the need
for possible EvalPlanQual rechecks, and ExecScanFetch would fail
an assertion (or just overwrite memory) if such a check was attempted
for a plan containing a pushed-down join. To fix, adjust the EPQ
machinery to skip some processing steps when scanrelid == 0, making
those the responsibility of scan's recheck method, which also has
the responsibility in this case of correctly populating the relevant
slot.
To allow foreign scans to gain control in the right place to make
use of this new facility, add a new, optional RecheckForeignScan
method. Also, allow a foreign scan to have a child plan, which can
be used to correctly populate the slot (or perhaps for something
else, but this is the only use currently envisioned).
KaiGai Kohei, reviewed by Robert Haas, Etsuro Fujita, and Kyotaro
Horiguchi.
2015-12-08 18:31:03 +01:00
|
|
|
/* Initialize any outer plan. */
|
|
|
|
|
if (outerPlan(node))
|
|
|
|
|
outerPlanState(scanstate) =
|
|
|
|
|
ExecInitNode(outerPlan(node), estate, eflags);
|
|
|
|
|
|
2011-02-20 06:17:18 +01:00
|
|
|
/*
|
Code review for foreign/custom join pushdown patch.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 included some design
decisions that seem pretty questionable to me, and there was quite a lot
of stuff not to like about the documentation and comments. Clean up
as follows:
* Consider foreign joins only between foreign tables on the same server,
rather than between any two foreign tables with the same underlying FDW
handler function. In most if not all cases, the FDW would simply have had
to apply the same-server restriction itself (far more expensively, both for
lack of caching and because it would be repeated for each combination of
input sub-joins), or else risk nasty bugs. Anyone who's really intent on
doing something outside this restriction can always use the
set_join_pathlist_hook.
* Rename fdw_ps_tlist/custom_ps_tlist to fdw_scan_tlist/custom_scan_tlist
to better reflect what they're for, and allow these custom scan tlists
to be used even for base relations.
* Change make_foreignscan() API to include passing the fdw_scan_tlist
value, since the FDW is required to set that. Backwards compatibility
doesn't seem like an adequate reason to expect FDWs to set it in some
ad-hoc extra step, and anyway existing FDWs can just pass NIL.
* Change the API of path-generating subroutines of add_paths_to_joinrel,
and in particular that of GetForeignJoinPaths and set_join_pathlist_hook,
so that various less-used parameters are passed in a struct rather than
as separate parameter-list entries. The objective here is to reduce the
probability that future additions to those parameter lists will result in
source-level API breaks for users of these hooks. It's possible that this
is even a small win for the core code, since most CPU architectures can't
pass more than half a dozen parameters efficiently anyway. I kept root,
joinrel, outerrel, innerrel, and jointype as separate parameters to reduce
code churn in joinpath.c --- in particular, putting jointype into the
struct would have been problematic because of the subroutines' habit of
changing their local copies of that variable.
* Avoid ad-hocery in ExecAssignScanProjectionInfo. It was probably all
right for it to know about IndexOnlyScan, but if the list is to grow
we should refactor the knowledge out to the callers.
* Restore nodeForeignscan.c's previous use of the relcache to avoid
extra GetFdwRoutine lookups for base-relation scans.
* Lots of cleanup of documentation and missed comments. Re-order some
code additions into more logical places.
2015-05-10 20:36:30 +02:00
|
|
|
* Tell the FDW to initialize the scan.
|
2011-02-20 06:17:18 +01:00
|
|
|
*/
|
2016-03-18 18:48:58 +01:00
|
|
|
if (node->operation != CMD_SELECT)
|
2021-08-12 10:02:29 +02:00
|
|
|
{
|
|
|
|
|
/*
|
|
|
|
|
* Direct modifications cannot be re-evaluated by EvalPlanQual, so
|
2022-02-03 07:15:00 +01:00
|
|
|
* don't bother preparing the FDW.
|
|
|
|
|
*
|
|
|
|
|
* In case of an inherited UPDATE/DELETE with foreign targets there
|
|
|
|
|
* can be direct-modify ForeignScan nodes in the EvalPlanQual subtree,
|
|
|
|
|
* so we need to ignore such ForeignScan nodes during EvalPlanQual
|
|
|
|
|
* processing. See also ExecForeignScan/ExecReScanForeignScan.
|
2021-08-12 10:02:29 +02:00
|
|
|
*/
|
|
|
|
|
if (estate->es_epq_active == NULL)
|
|
|
|
|
fdwroutine->BeginDirectModify(scanstate, eflags);
|
|
|
|
|
}
|
2016-03-18 18:48:58 +01:00
|
|
|
else
|
|
|
|
|
fdwroutine->BeginForeignScan(scanstate, eflags);
|
2011-02-20 06:17:18 +01:00
|
|
|
|
|
|
|
|
return scanstate;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
|
* ExecEndForeignScan
|
|
|
|
|
*
|
|
|
|
|
* frees any storage allocated through C routines.
|
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
ExecEndForeignScan(ForeignScanState *node)
|
|
|
|
|
{
|
2016-03-18 18:48:58 +01:00
|
|
|
ForeignScan *plan = (ForeignScan *) node->ss.ps.plan;
|
2021-08-12 10:02:29 +02:00
|
|
|
EState *estate = node->ss.ps.state;
|
2016-03-18 18:48:58 +01:00
|
|
|
|
2011-02-20 06:17:18 +01:00
|
|
|
/* Let the FDW shut down */
|
2016-03-18 18:48:58 +01:00
|
|
|
if (plan->operation != CMD_SELECT)
|
2021-08-12 10:02:29 +02:00
|
|
|
{
|
|
|
|
|
if (estate->es_epq_active == NULL)
|
|
|
|
|
node->fdwroutine->EndDirectModify(node);
|
|
|
|
|
}
|
2016-03-18 18:48:58 +01:00
|
|
|
else
|
|
|
|
|
node->fdwroutine->EndForeignScan(node);
|
2011-02-20 06:17:18 +01:00
|
|
|
|
Allow foreign and custom joins to handle EvalPlanQual rechecks.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 provided basic
infrastructure for allowing a foreign data wrapper or custom scan
provider to replace a join of one or more tables with a scan.
However, this infrastructure failed to take into account the need
for possible EvalPlanQual rechecks, and ExecScanFetch would fail
an assertion (or just overwrite memory) if such a check was attempted
for a plan containing a pushed-down join. To fix, adjust the EPQ
machinery to skip some processing steps when scanrelid == 0, making
those the responsibility of scan's recheck method, which also has
the responsibility in this case of correctly populating the relevant
slot.
To allow foreign scans to gain control in the right place to make
use of this new facility, add a new, optional RecheckForeignScan
method. Also, allow a foreign scan to have a child plan, which can
be used to correctly populate the slot (or perhaps for something
else, but this is the only use currently envisioned).
KaiGai Kohei, reviewed by Robert Haas, Etsuro Fujita, and Kyotaro
Horiguchi.
2015-12-08 18:31:03 +01:00
|
|
|
/* Shut down any outer plan. */
|
|
|
|
|
if (outerPlanState(node))
|
|
|
|
|
ExecEndNode(outerPlanState(node));
|
|
|
|
|
|
2011-02-20 06:17:18 +01:00
|
|
|
/* Free the exprcontext */
|
|
|
|
|
ExecFreeExprContext(&node->ss.ps);
|
|
|
|
|
|
|
|
|
|
/* clean out the tuple table */
|
Don't require return slots for nodes without projection.
In a lot of nodes the return slot is not required. That can either be
because the node doesn't do any projection (say an Append node), or
because the node does perform projections but the projection is
optimized away because the projection would yield an identical row.
Slots aren't that small, especially for wide rows, so it's worthwhile
to avoid creating them. It's not possible to just skip creating the
slot - it's currently used to determine the tuple descriptor returned
by ExecGetResultType(). So separate the determination of the result
type from the slot creation. The work previously done internally
ExecInitResultTupleSlotTL() can now also be done separately with
ExecInitResultTypeTL() and ExecInitResultSlot(). That way nodes that
aren't guaranteed to need a result slot, can use
ExecInitResultTypeTL() to determine the result type of the node, and
ExecAssignScanProjectionInfo() (via
ExecConditionalAssignProjectionInfo()) determines that a result slot
is needed, it is created with ExecInitResultSlot().
Besides the advantage of avoiding to create slots that then are
unused, this is necessary preparation for later patches around tuple
table slot abstraction. In particular separating the return descriptor
and slot is a prerequisite to allow JITing of tuple deforming with
knowledge of the underlying tuple format, and to avoid unnecessarily
creating JITed tuple deforming for virtual slots.
This commit removes a redundant argument from
ExecInitResultTupleSlotTL(). While this commit touches a lot of the
relevant lines anyway, it'd normally still not worthwhile to cause
breakage, except that aforementioned later commits will touch *all*
ExecInitResultTupleSlotTL() callers anyway (but fits worse
thematically).
Author: Andres Freund
Discussion: https://postgr.es/m/20181105210039.hh4vvi4vwoq5ba2q@alap3.anarazel.de
2018-11-10 02:19:39 +01:00
|
|
|
if (node->ss.ps.ps_ResultTupleSlot)
|
|
|
|
|
ExecClearTuple(node->ss.ps.ps_ResultTupleSlot);
|
2011-02-20 06:17:18 +01:00
|
|
|
ExecClearTuple(node->ss.ss_ScanTupleSlot);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
|
* ExecReScanForeignScan
|
|
|
|
|
*
|
|
|
|
|
* Rescans the relation.
|
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
ExecReScanForeignScan(ForeignScanState *node)
|
|
|
|
|
{
|
2022-02-03 07:15:00 +01:00
|
|
|
ForeignScan *plan = (ForeignScan *) node->ss.ps.plan;
|
|
|
|
|
EState *estate = node->ss.ps.state;
|
Allow foreign and custom joins to handle EvalPlanQual rechecks.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 provided basic
infrastructure for allowing a foreign data wrapper or custom scan
provider to replace a join of one or more tables with a scan.
However, this infrastructure failed to take into account the need
for possible EvalPlanQual rechecks, and ExecScanFetch would fail
an assertion (or just overwrite memory) if such a check was attempted
for a plan containing a pushed-down join. To fix, adjust the EPQ
machinery to skip some processing steps when scanrelid == 0, making
those the responsibility of scan's recheck method, which also has
the responsibility in this case of correctly populating the relevant
slot.
To allow foreign scans to gain control in the right place to make
use of this new facility, add a new, optional RecheckForeignScan
method. Also, allow a foreign scan to have a child plan, which can
be used to correctly populate the slot (or perhaps for something
else, but this is the only use currently envisioned).
KaiGai Kohei, reviewed by Robert Haas, Etsuro Fujita, and Kyotaro
Horiguchi.
2015-12-08 18:31:03 +01:00
|
|
|
PlanState *outerPlan = outerPlanState(node);
|
|
|
|
|
|
2022-02-03 07:15:00 +01:00
|
|
|
/*
|
|
|
|
|
* Ignore direct modifications when EvalPlanQual is active --- they are
|
|
|
|
|
* irrelevant for EvalPlanQual rechecking
|
|
|
|
|
*/
|
|
|
|
|
if (estate->es_epq_active != NULL && plan->operation != CMD_SELECT)
|
|
|
|
|
return;
|
|
|
|
|
|
2011-02-20 06:17:18 +01:00
|
|
|
node->fdwroutine->ReScanForeignScan(node);
|
|
|
|
|
|
Allow foreign and custom joins to handle EvalPlanQual rechecks.
Commit e7cb7ee14555cc9c5773e2c102efd6371f6f2005 provided basic
infrastructure for allowing a foreign data wrapper or custom scan
provider to replace a join of one or more tables with a scan.
However, this infrastructure failed to take into account the need
for possible EvalPlanQual rechecks, and ExecScanFetch would fail
an assertion (or just overwrite memory) if such a check was attempted
for a plan containing a pushed-down join. To fix, adjust the EPQ
machinery to skip some processing steps when scanrelid == 0, making
those the responsibility of scan's recheck method, which also has
the responsibility in this case of correctly populating the relevant
slot.
To allow foreign scans to gain control in the right place to make
use of this new facility, add a new, optional RecheckForeignScan
method. Also, allow a foreign scan to have a child plan, which can
be used to correctly populate the slot (or perhaps for something
else, but this is the only use currently envisioned).
KaiGai Kohei, reviewed by Robert Haas, Etsuro Fujita, and Kyotaro
Horiguchi.
2015-12-08 18:31:03 +01:00
|
|
|
/*
|
|
|
|
|
* If chgParam of subnode is not null then plan will be re-scanned by
|
|
|
|
|
* first ExecProcNode. outerPlan may also be NULL, in which case there is
|
|
|
|
|
* nothing to rescan at all.
|
|
|
|
|
*/
|
|
|
|
|
if (outerPlan != NULL && outerPlan->chgParam == NULL)
|
|
|
|
|
ExecReScan(outerPlan);
|
|
|
|
|
|
2011-02-20 06:17:18 +01:00
|
|
|
ExecScanReScan(&node->ss);
|
|
|
|
|
}
|
2016-02-03 18:46:18 +01:00
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
|
* ExecForeignScanEstimate
|
|
|
|
|
*
|
|
|
|
|
* Informs size of the parallel coordination information, if any
|
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
ExecForeignScanEstimate(ForeignScanState *node, ParallelContext *pcxt)
|
|
|
|
|
{
|
|
|
|
|
FdwRoutine *fdwroutine = node->fdwroutine;
|
|
|
|
|
|
|
|
|
|
if (fdwroutine->EstimateDSMForeignScan)
|
|
|
|
|
{
|
|
|
|
|
node->pscan_len = fdwroutine->EstimateDSMForeignScan(node, pcxt);
|
|
|
|
|
shm_toc_estimate_chunk(&pcxt->estimator, node->pscan_len);
|
|
|
|
|
shm_toc_estimate_keys(&pcxt->estimator, 1);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
|
* ExecForeignScanInitializeDSM
|
|
|
|
|
*
|
|
|
|
|
* Initialize the parallel coordination information
|
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
ExecForeignScanInitializeDSM(ForeignScanState *node, ParallelContext *pcxt)
|
|
|
|
|
{
|
|
|
|
|
FdwRoutine *fdwroutine = node->fdwroutine;
|
|
|
|
|
|
|
|
|
|
if (fdwroutine->InitializeDSMForeignScan)
|
|
|
|
|
{
|
|
|
|
|
int plan_node_id = node->ss.ps.plan->plan_node_id;
|
|
|
|
|
void *coordinate;
|
|
|
|
|
|
|
|
|
|
coordinate = shm_toc_allocate(pcxt->toc, node->pscan_len);
|
|
|
|
|
fdwroutine->InitializeDSMForeignScan(node, pcxt, coordinate);
|
|
|
|
|
shm_toc_insert(pcxt->toc, plan_node_id, coordinate);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
Separate reinitialization of shared parallel-scan state from ExecReScan.
Previously, the parallel executor logic did reinitialization of shared
state within the ExecReScan code for parallel-aware scan nodes. This is
problematic, because it means that the ExecReScan call has to occur
synchronously (ie, during the parent Gather node's ReScan call). That is
swimming very much against the tide so far as the ExecReScan machinery is
concerned; the fact that it works at all today depends on a lot of fragile
assumptions, such as that no plan node between Gather and a parallel-aware
scan node is parameterized. Another objection is that because ExecReScan
might be called in workers as well as the leader, hacky extra tests are
needed in some places to prevent unwanted shared-state resets.
Hence, let's separate this code into two functions, a ReInitializeDSM
call and the ReScan call proper. ReInitializeDSM is called only in
the leader and is guaranteed to run before we start new workers.
ReScan is returned to its traditional function of resetting only local
state, which means that ExecReScan's usual habits of delaying or
eliminating child rescan calls are safe again.
As with the preceding commit 7df2c1f8d, it doesn't seem to be necessary
to make these changes in 9.6, which is a good thing because the FDW and
CustomScan APIs are impacted.
Discussion: https://postgr.es/m/CAA4eK1JkByysFJNh9M349u_nNjqETuEnY_y1VUc_kJiU0bxtaQ@mail.gmail.com
2017-08-30 19:18:16 +02:00
|
|
|
* ExecForeignScanReInitializeDSM
|
|
|
|
|
*
|
|
|
|
|
* Reset shared state before beginning a fresh scan.
|
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
ExecForeignScanReInitializeDSM(ForeignScanState *node, ParallelContext *pcxt)
|
|
|
|
|
{
|
|
|
|
|
FdwRoutine *fdwroutine = node->fdwroutine;
|
|
|
|
|
|
|
|
|
|
if (fdwroutine->ReInitializeDSMForeignScan)
|
|
|
|
|
{
|
|
|
|
|
int plan_node_id = node->ss.ps.plan->plan_node_id;
|
|
|
|
|
void *coordinate;
|
|
|
|
|
|
|
|
|
|
coordinate = shm_toc_lookup(pcxt->toc, plan_node_id, false);
|
|
|
|
|
fdwroutine->ReInitializeDSMForeignScan(node, pcxt, coordinate);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
|
* ExecForeignScanInitializeWorker
|
2016-02-03 18:46:18 +01:00
|
|
|
*
|
|
|
|
|
* Initialization according to the parallel coordination information
|
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
void
|
2017-11-17 02:28:11 +01:00
|
|
|
ExecForeignScanInitializeWorker(ForeignScanState *node,
|
|
|
|
|
ParallelWorkerContext *pwcxt)
|
2016-02-03 18:46:18 +01:00
|
|
|
{
|
|
|
|
|
FdwRoutine *fdwroutine = node->fdwroutine;
|
|
|
|
|
|
|
|
|
|
if (fdwroutine->InitializeWorkerForeignScan)
|
|
|
|
|
{
|
|
|
|
|
int plan_node_id = node->ss.ps.plan->plan_node_id;
|
|
|
|
|
void *coordinate;
|
|
|
|
|
|
2017-11-17 02:28:11 +01:00
|
|
|
coordinate = shm_toc_lookup(pwcxt->toc, plan_node_id, false);
|
|
|
|
|
fdwroutine->InitializeWorkerForeignScan(node, pwcxt->toc, coordinate);
|
2016-02-03 18:46:18 +01:00
|
|
|
}
|
|
|
|
|
}
|
2017-02-26 09:06:49 +01:00
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
|
* ExecShutdownForeignScan
|
|
|
|
|
*
|
|
|
|
|
* Gives FDW chance to stop asynchronous resource consumption
|
|
|
|
|
* and release any resources still held.
|
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
ExecShutdownForeignScan(ForeignScanState *node)
|
|
|
|
|
{
|
|
|
|
|
FdwRoutine *fdwroutine = node->fdwroutine;
|
|
|
|
|
|
|
|
|
|
if (fdwroutine->ShutdownForeignScan)
|
|
|
|
|
fdwroutine->ShutdownForeignScan(node);
|
|
|
|
|
}
|
Add support for asynchronous execution.
This implements asynchronous execution, which runs multiple parts of a
non-parallel-aware Append concurrently rather than serially to improve
performance when possible. Currently, the only node type that can be
run concurrently is a ForeignScan that is an immediate child of such an
Append. In the case where such ForeignScans access data on different
remote servers, this would run those ForeignScans concurrently, and
overlap the remote operations to be performed simultaneously, so it'll
improve the performance especially when the operations involve
time-consuming ones such as remote join and remote aggregation.
We may extend this to other node types such as joins or aggregates over
ForeignScans in the future.
This also adds the support for postgres_fdw, which is enabled by the
table-level/server-level option "async_capable". The default is false.
Robert Haas, Kyotaro Horiguchi, Thomas Munro, and myself. This commit
is mostly based on the patch proposed by Robert Haas, but also uses
stuff from the patch proposed by Kyotaro Horiguchi and from the patch
proposed by Thomas Munro. Reviewed by Kyotaro Horiguchi, Konstantin
Knizhnik, Andrey Lepikhov, Movead Li, Thomas Munro, Justin Pryzby, and
others.
Discussion: https://postgr.es/m/CA%2BTgmoaXQEt4tZ03FtQhnzeDEMzBck%2BLrni0UWHVVgOTnA6C1w%40mail.gmail.com
Discussion: https://postgr.es/m/CA%2BhUKGLBRyu0rHrDCMC4%3DRn3252gogyp1SjOgG8SEKKZv%3DFwfQ%40mail.gmail.com
Discussion: https://postgr.es/m/20200228.170650.667613673625155850.horikyota.ntt%40gmail.com
2021-03-31 11:45:00 +02:00
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
|
* ExecAsyncForeignScanRequest
|
|
|
|
|
*
|
|
|
|
|
* Asynchronously request a tuple from a designed async-capable node
|
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
ExecAsyncForeignScanRequest(AsyncRequest *areq)
|
|
|
|
|
{
|
|
|
|
|
ForeignScanState *node = (ForeignScanState *) areq->requestee;
|
|
|
|
|
FdwRoutine *fdwroutine = node->fdwroutine;
|
|
|
|
|
|
|
|
|
|
Assert(fdwroutine->ForeignAsyncRequest != NULL);
|
|
|
|
|
fdwroutine->ForeignAsyncRequest(areq);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
|
* ExecAsyncForeignScanConfigureWait
|
|
|
|
|
*
|
|
|
|
|
* In async mode, configure for a wait
|
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
ExecAsyncForeignScanConfigureWait(AsyncRequest *areq)
|
|
|
|
|
{
|
|
|
|
|
ForeignScanState *node = (ForeignScanState *) areq->requestee;
|
|
|
|
|
FdwRoutine *fdwroutine = node->fdwroutine;
|
|
|
|
|
|
|
|
|
|
Assert(fdwroutine->ForeignAsyncConfigureWait != NULL);
|
|
|
|
|
fdwroutine->ForeignAsyncConfigureWait(areq);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
|
* ExecAsyncForeignScanNotify
|
|
|
|
|
*
|
|
|
|
|
* Callback invoked when a relevant event has occurred
|
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
ExecAsyncForeignScanNotify(AsyncRequest *areq)
|
|
|
|
|
{
|
|
|
|
|
ForeignScanState *node = (ForeignScanState *) areq->requestee;
|
|
|
|
|
FdwRoutine *fdwroutine = node->fdwroutine;
|
|
|
|
|
|
|
|
|
|
Assert(fdwroutine->ForeignAsyncNotify != NULL);
|
|
|
|
|
fdwroutine->ForeignAsyncNotify(areq);
|
|
|
|
|
}
|
