2014-11-07 23:26:02 +01:00
|
|
|
/* ------------------------------------------------------------------------
|
|
|
|
|
*
|
|
|
|
|
* nodeCustom.c
|
|
|
|
|
* Routines to handle execution of custom scan node
|
|
|
|
|
*
|
2018-01-03 05:30:12 +01:00
|
|
|
* Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group
|
2014-11-07 23:26:02 +01:00
|
|
|
* Portions Copyright (c) 1994, Regents of the University of California
|
|
|
|
|
*
|
|
|
|
|
* ------------------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
#include "postgres.h"
|
|
|
|
|
|
2016-02-03 18:46:18 +01:00
|
|
|
#include "access/parallel.h"
|
2014-11-07 23:26:02 +01:00
|
|
|
#include "executor/executor.h"
|
|
|
|
|
#include "executor/nodeCustom.h"
|
|
|
|
|
#include "nodes/execnodes.h"
|
|
|
|
|
#include "nodes/plannodes.h"
|
2017-07-26 02:37:17 +02:00
|
|
|
#include "miscadmin.h"
|
2014-11-07 23:26:02 +01:00
|
|
|
#include "parser/parsetree.h"
|
|
|
|
|
#include "utils/hsearch.h"
|
|
|
|
|
#include "utils/memutils.h"
|
|
|
|
|
#include "utils/rel.h"
|
|
|
|
|
|
2017-07-17 09:33:49 +02:00
|
|
|
|
|
|
|
|
static TupleTableSlot *ExecCustomScan(PlanState *pstate);
|
|
|
|
|
|
|
|
|
|
|
2014-11-07 23:26:02 +01:00
|
|
|
CustomScanState *
|
|
|
|
|
ExecInitCustomScan(CustomScan *cscan, EState *estate, int eflags)
|
|
|
|
|
{
|
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
|
|
|
CustomScanState *css;
|
|
|
|
|
Relation scan_rel = NULL;
|
|
|
|
|
Index scanrelid = cscan->scan.scanrelid;
|
|
|
|
|
Index tlistvarno;
|
2014-11-07 23:26:02 +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
|
|
|
/*
|
|
|
|
|
* Allocate the CustomScanState object. We let the custom scan provider
|
|
|
|
|
* do the palloc, in case it wants to make a larger object that embeds
|
|
|
|
|
* CustomScanState as the first field. It must set the node tag and the
|
|
|
|
|
* methods field correctly at this time. Other standard fields should be
|
|
|
|
|
* set to zero.
|
|
|
|
|
*/
|
2017-01-27 01:47:03 +01:00
|
|
|
css = castNode(CustomScanState,
|
|
|
|
|
cscan->methods->CreateCustomScanState(cscan));
|
2014-11-07 23:26:02 +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
|
|
|
/* ensure flags is filled correctly */
|
|
|
|
|
css->flags = cscan->flags;
|
|
|
|
|
|
2014-11-07 23:26:02 +01:00
|
|
|
/* fill up fields of ScanState */
|
|
|
|
|
css->ss.ps.plan = &cscan->scan.plan;
|
|
|
|
|
css->ss.ps.state = estate;
|
2017-07-17 09:33:49 +02:00
|
|
|
css->ss.ps.ExecProcNode = ExecCustomScan;
|
2014-11-07 23:26:02 +01:00
|
|
|
|
|
|
|
|
/* create expression context for node */
|
|
|
|
|
ExecAssignExprContext(estate, &css->ss.ps);
|
|
|
|
|
|
2015-05-01 14:50:35 +02:00
|
|
|
/*
|
2018-10-06 21:49:37 +02:00
|
|
|
* open the scan relation, if any
|
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
|
|
|
if (scanrelid > 0)
|
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
|
|
|
scan_rel = ExecOpenScanRelation(estate, scanrelid, eflags);
|
2015-05-01 14:50:35 +02:00
|
|
|
css->ss.ss_currentRelation = scan_rel;
|
|
|
|
|
}
|
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 custom scan provider provided a
|
|
|
|
|
* targetlist describing the scan tuples, use that; else use base
|
|
|
|
|
* relation's rowtype.
|
|
|
|
|
*/
|
|
|
|
|
if (cscan->custom_scan_tlist != NIL || scan_rel == NULL)
|
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
|
|
|
TupleDesc scan_tupdesc;
|
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
|
|
|
scan_tupdesc = ExecTypeFromTL(cscan->custom_scan_tlist, false);
|
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, &css->ss, scan_tupdesc, &TTSOpsVirtual);
|
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
|
|
|
|
|
{
|
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, &css->ss, RelationGetDescr(scan_rel),
|
|
|
|
|
&TTSOpsVirtual);
|
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
|
|
|
}
|
2014-11-07 23:26:02 +01:00
|
|
|
|
|
|
|
|
/*
|
2018-02-17 06:17:38 +01:00
|
|
|
* Initialize result slot, type and projection.
|
2014-11-07 23:26:02 +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
|
|
|
ExecInitResultTupleSlotTL(&css->ss.ps, &TTSOpsVirtual);
|
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(&css->ss, tlistvarno);
|
2014-11-07 23:26:02 +01:00
|
|
|
|
2018-02-17 06:17:38 +01:00
|
|
|
/* initialize child expressions */
|
|
|
|
|
css->ss.ps.qual =
|
|
|
|
|
ExecInitQual(cscan->scan.plan.qual, (PlanState *) css);
|
|
|
|
|
|
2014-11-07 23:26:02 +01:00
|
|
|
/*
|
|
|
|
|
* The callback of custom-scan provider applies the final initialization
|
|
|
|
|
* of the custom-scan-state node according to its logic.
|
|
|
|
|
*/
|
|
|
|
|
css->methods->BeginCustomScan(css, estate, eflags);
|
|
|
|
|
|
|
|
|
|
return css;
|
|
|
|
|
}
|
|
|
|
|
|
2017-07-17 09:33:49 +02:00
|
|
|
static TupleTableSlot *
|
|
|
|
|
ExecCustomScan(PlanState *pstate)
|
2014-11-07 23:26:02 +01:00
|
|
|
{
|
2017-07-17 09:33:49 +02:00
|
|
|
CustomScanState *node = castNode(CustomScanState, pstate);
|
|
|
|
|
|
2017-07-26 02:37:17 +02:00
|
|
|
CHECK_FOR_INTERRUPTS();
|
|
|
|
|
|
2014-11-07 23:26:02 +01:00
|
|
|
Assert(node->methods->ExecCustomScan != NULL);
|
|
|
|
|
return node->methods->ExecCustomScan(node);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
ExecEndCustomScan(CustomScanState *node)
|
|
|
|
|
{
|
|
|
|
|
Assert(node->methods->EndCustomScan != NULL);
|
|
|
|
|
node->methods->EndCustomScan(node);
|
|
|
|
|
|
|
|
|
|
/* Free the exprcontext */
|
|
|
|
|
ExecFreeExprContext(&node->ss.ps);
|
|
|
|
|
|
|
|
|
|
/* Clean out the tuple table */
|
|
|
|
|
ExecClearTuple(node->ss.ps.ps_ResultTupleSlot);
|
2015-05-01 14:50:35 +02:00
|
|
|
ExecClearTuple(node->ss.ss_ScanTupleSlot);
|
2014-11-07 23:26:02 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
ExecReScanCustomScan(CustomScanState *node)
|
|
|
|
|
{
|
|
|
|
|
Assert(node->methods->ReScanCustomScan != NULL);
|
|
|
|
|
node->methods->ReScanCustomScan(node);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
ExecCustomMarkPos(CustomScanState *node)
|
|
|
|
|
{
|
|
|
|
|
if (!node->methods->MarkPosCustomScan)
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
|
2015-12-11 04:05:27 +01:00
|
|
|
errmsg("custom scan \"%s\" does not support MarkPos",
|
2014-11-07 23:26:02 +01:00
|
|
|
node->methods->CustomName)));
|
|
|
|
|
node->methods->MarkPosCustomScan(node);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
ExecCustomRestrPos(CustomScanState *node)
|
|
|
|
|
{
|
|
|
|
|
if (!node->methods->RestrPosCustomScan)
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
|
2015-12-11 04:05:27 +01:00
|
|
|
errmsg("custom scan \"%s\" does not support MarkPos",
|
2014-11-07 23:26:02 +01:00
|
|
|
node->methods->CustomName)));
|
|
|
|
|
node->methods->RestrPosCustomScan(node);
|
|
|
|
|
}
|
2016-02-03 18:46:18 +01:00
|
|
|
|
|
|
|
|
void
|
|
|
|
|
ExecCustomScanEstimate(CustomScanState *node, ParallelContext *pcxt)
|
|
|
|
|
{
|
|
|
|
|
const CustomExecMethods *methods = node->methods;
|
|
|
|
|
|
|
|
|
|
if (methods->EstimateDSMCustomScan)
|
|
|
|
|
{
|
|
|
|
|
node->pscan_len = methods->EstimateDSMCustomScan(node, pcxt);
|
|
|
|
|
shm_toc_estimate_chunk(&pcxt->estimator, node->pscan_len);
|
|
|
|
|
shm_toc_estimate_keys(&pcxt->estimator, 1);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
ExecCustomScanInitializeDSM(CustomScanState *node, ParallelContext *pcxt)
|
|
|
|
|
{
|
|
|
|
|
const CustomExecMethods *methods = node->methods;
|
|
|
|
|
|
|
|
|
|
if (methods->InitializeDSMCustomScan)
|
|
|
|
|
{
|
|
|
|
|
int plan_node_id = node->ss.ps.plan->plan_node_id;
|
|
|
|
|
void *coordinate;
|
|
|
|
|
|
|
|
|
|
coordinate = shm_toc_allocate(pcxt->toc, node->pscan_len);
|
|
|
|
|
methods->InitializeDSMCustomScan(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
|
|
|
void
|
|
|
|
|
ExecCustomScanReInitializeDSM(CustomScanState *node, ParallelContext *pcxt)
|
|
|
|
|
{
|
|
|
|
|
const CustomExecMethods *methods = node->methods;
|
|
|
|
|
|
|
|
|
|
if (methods->ReInitializeDSMCustomScan)
|
|
|
|
|
{
|
|
|
|
|
int plan_node_id = node->ss.ps.plan->plan_node_id;
|
|
|
|
|
void *coordinate;
|
|
|
|
|
|
|
|
|
|
coordinate = shm_toc_lookup(pcxt->toc, plan_node_id, false);
|
|
|
|
|
methods->ReInitializeDSMCustomScan(node, pcxt, coordinate);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2016-02-03 18:46:18 +01:00
|
|
|
void
|
2017-11-17 02:28:11 +01:00
|
|
|
ExecCustomScanInitializeWorker(CustomScanState *node,
|
|
|
|
|
ParallelWorkerContext *pwcxt)
|
2016-02-03 18:46:18 +01:00
|
|
|
{
|
|
|
|
|
const CustomExecMethods *methods = node->methods;
|
|
|
|
|
|
|
|
|
|
if (methods->InitializeWorkerCustomScan)
|
|
|
|
|
{
|
|
|
|
|
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);
|
|
|
|
|
methods->InitializeWorkerCustomScan(node, pwcxt->toc, coordinate);
|
2016-02-03 18:46:18 +01:00
|
|
|
}
|
|
|
|
|
}
|
2017-02-26 09:06:49 +01:00
|
|
|
|
|
|
|
|
void
|
|
|
|
|
ExecShutdownCustomScan(CustomScanState *node)
|
|
|
|
|
{
|
|
|
|
|
const CustomExecMethods *methods = node->methods;
|
|
|
|
|
|
|
|
|
|
if (methods->ShutdownCustomScan)
|
|
|
|
|
methods->ShutdownCustomScan(node);
|
|
|
|
|
}
|
