opensourcemirror
/
postgresql
mirror of git://git.postgresql.org/git/postgresql.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Reduce branches in heapgetpage()'s per-tuple loop 

Until now, heapgetpage()'s loop over all tuples performed some conditional
checks for each tuple, even though condition did not change across the loop.

This commit fixes that by moving the loop into an inline function. By calling
it with different constant arguments, the compiler can generate an optimized
loop for the different conditions, at the price of two per-page checks.

For cases of all-visible tables and an isolation level other than
serializable, speedups of up to 25% have been measured.

Reviewed-by: John Naylor <johncnaylorls@gmail.com>
Reviewed-by: Zhang Mingli <zmlpostgres@gmail.com>
Tested-by: Quan Zongliang <quanzongliang@yeah.net>
Discussion: https://postgr.es/m/20230716015656.xjvemfbp5fysjiea@awork3.anarazel.de
Discussion: https://postgr.es/m/2ef7ff1b-3d18-2283-61b1-bbd25fc6c7ce@yeah.net
This commit is contained in:
Andres Freund 2024-04-06 20:51:07 -07:00
parent 41c51f0c68
commit a97bbe1f1d
1 changed files with 74 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

102
src/backend/access/heap/heapam.c
View File

@ -364,6 +364,56 @@ heap_setscanlimits(TableScanDesc sscan, BlockNumber startBlk, BlockNumber numBlk
scan->rs_numblocks = numBlks;
}
/*
* Per-tuple loop for heapgetpage() in pagemode. Pulled out so it can be
* called multiple times, with constant arguments for all_visible,
* check_serializable.
*/
pg_attribute_always_inline
static int
heapgetpage_collect(HeapScanDesc scan, Snapshot snapshot,
Page page, Buffer buffer,
BlockNumber block, int lines,
bool all_visible, bool check_serializable)
{
int ntup = 0;
OffsetNumber lineoff;
for (lineoff = FirstOffsetNumber; lineoff <= lines; lineoff++)
{
ItemId lpp = PageGetItemId(page, lineoff);
HeapTupleData loctup;
bool valid;
if (!ItemIdIsNormal(lpp))
continue;
loctup.t_data = (HeapTupleHeader) PageGetItem(page, lpp);
loctup.t_len = ItemIdGetLength(lpp);
loctup.t_tableOid = RelationGetRelid(scan->rs_base.rs_rd);
ItemPointerSet(&(loctup.t_self), block, lineoff);
if (all_visible)
valid = true;
else
valid = HeapTupleSatisfiesVisibility(&loctup, snapshot, buffer);
if (check_serializable)
HeapCheckForSerializableConflictOut(valid, scan->rs_base.rs_rd,
&loctup, buffer, snapshot);
if (valid)
{
scan->rs_vistuples[ntup] = lineoff;
ntup++;
}
}
Assert(ntup <= MaxHeapTuplesPerPage);
return ntup;
}
/*
* heap_prepare_pagescan - Prepare current scan page to be scanned in pagemode
*
@ -379,9 +429,8 @@ heap_prepare_pagescan(TableScanDesc sscan)
Snapshot snapshot;
Page page;
int lines;
int ntup;
OffsetNumber lineoff;
bool all_visible;
bool check_serializable;
Assert(BufferGetBlockNumber(buffer) == block);
@ -403,7 +452,6 @@ heap_prepare_pagescan(TableScanDesc sscan)
page = BufferGetPage(buffer);
lines = PageGetMaxOffsetNumber(page);
ntup = 0;
/*
* If the all-visible flag indicates that all tuples on the page are
@ -426,37 +474,35 @@ heap_prepare_pagescan(TableScanDesc sscan)
* tuple for visibility the hard way.
*/
all_visible = PageIsAllVisible(page) && !snapshot->takenDuringRecovery;
check_serializable =
CheckForSerializableConflictOutNeeded(scan->rs_base.rs_rd, snapshot);
for (lineoff = FirstOffsetNumber; lineoff <= lines; lineoff++)
/*
* We call heapgetpage_collect() with constant arguments, to get the
* compiler to constant fold the constant arguments. Separate calls with
* constant arguments, rather than variables, are needed on several
* compilers to actually perform constant folding.
*/
if (likely(all_visible))
{
ItemId lpp = PageGetItemId(page, lineoff);
HeapTupleData loctup;
bool valid;
if (!ItemIdIsNormal(lpp))
continue;
loctup.t_tableOid = RelationGetRelid(scan->rs_base.rs_rd);
loctup.t_data = (HeapTupleHeader) PageGetItem(page, lpp);
loctup.t_len = ItemIdGetLength(lpp);
ItemPointerSet(&(loctup.t_self), block, lineoff);
if (all_visible)
valid = true;
if (likely(!check_serializable))
scan->rs_ntuples = heapgetpage_collect(scan, snapshot, page, buffer,
block, lines, true, false);
else
valid = HeapTupleSatisfiesVisibility(&loctup, snapshot, buffer);
HeapCheckForSerializableConflictOut(valid, scan->rs_base.rs_rd,
&loctup, buffer, snapshot);
if (valid)
scan->rs_vistuples[ntup++] = lineoff;
scan->rs_ntuples = heapgetpage_collect(scan, snapshot, page, buffer,
block, lines, true, true);
}
else
{
if (likely(!check_serializable))
scan->rs_ntuples = heapgetpage_collect(scan, snapshot, page, buffer,
block, lines, false, false);
else
scan->rs_ntuples = heapgetpage_collect(scan, snapshot, page, buffer,
block, lines, false, true);
}
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
Assert(ntup <= MaxHeapTuplesPerPage);
scan->rs_ntuples = ntup;
}
/*