mirror of
https://github.com/postgres/postgres.git
synced 2025-06-14 18:42:34 +03:00
Reply-To: hackers@hub.org, Dan McGuirk <mcguirk@indirect.com> To: hackers@hub.org Subject: [HACKERS] tmin writeback optimization I was doing some profiling of the backend, and noticed that during a certain benchmark I was running somewhere between 30% and 75% of the backend's CPU time was being spent in calls to TransactionIdDidCommit() from HeapTupleSatisfiesNow() or HeapTupleSatisfiesItself() to determine that changed rows' transactions had in fact been committed even though the rows' tmin values had not yet been set. When a query looks at a given row, it needs to figure out whether the transaction that changed the row has been committed and hence it should pay attention to the row, or whether on the other hand the transaction is still in progress or has been aborted and hence the row should be ignored. If a tmin value is set, it is known definitively that the row's transaction has been committed. However, if tmin is not set, the transaction referred to in xmin must be looked up in pg_log, and this is what the backend was spending a lot of time doing during my benchmark. So, implementing a method suggested by Vadim, I created the following patch that, the first time a query finds a committed row whose tmin value is not set, sets it, and marks the buffer where the row is stored as dirty. (It works for tmax, too.) This doesn't result in the boost in real time performance I was hoping for, however it does decrease backend CPU usage by up to two-thirds in certain situations, so it could be rather beneficial in high-concurrency settings.
150 lines
3.7 KiB
C
150 lines
3.7 KiB
C
/*-------------------------------------------------------------------------
|
|
*
|
|
* heapvalid.c--
|
|
* heap tuple qualification validity checking code
|
|
*
|
|
* Copyright (c) 1994, Regents of the University of California
|
|
*
|
|
*
|
|
* IDENTIFICATION
|
|
* $Header: /cvsroot/pgsql/src/backend/access/common/Attic/heapvalid.c,v 1.13 1997/03/28 07:03:53 scrappy Exp $
|
|
*
|
|
*-------------------------------------------------------------------------
|
|
*/
|
|
|
|
#include <postgres.h>
|
|
|
|
#include <fmgr.h>
|
|
#include <access/heaptuple.h>
|
|
#include <access/valid.h>
|
|
#include <access/xact.h>
|
|
#include <storage/bufpage.h>
|
|
#include <utils/rel.h>
|
|
#include <utils/tqual.h>
|
|
#include <storage/bufmgr.h>
|
|
|
|
/* ----------------
|
|
* heap_keytest
|
|
*
|
|
* Test a heap tuple with respect to a scan key.
|
|
* ----------------
|
|
*/
|
|
bool
|
|
heap_keytest(HeapTuple t,
|
|
TupleDesc tupdesc,
|
|
int nkeys,
|
|
ScanKey keys)
|
|
{
|
|
bool isnull;
|
|
Datum atp;
|
|
int test;
|
|
|
|
for (; nkeys--; keys++) {
|
|
atp = (Datum)heap_getattr(t, InvalidBuffer,
|
|
keys->sk_attno,
|
|
tupdesc,
|
|
&isnull);
|
|
|
|
if (isnull)
|
|
/* XXX eventually should check if SK_ISNULL */
|
|
return false;
|
|
|
|
if (keys->sk_flags & SK_ISNULL) {
|
|
return (false);
|
|
}
|
|
|
|
if (keys->sk_flags & SK_COMMUTE)
|
|
test = (long) FMGR_PTR2(keys->sk_func, keys->sk_procedure,
|
|
keys->sk_argument, atp);
|
|
else
|
|
test = (long) FMGR_PTR2(keys->sk_func, keys->sk_procedure,
|
|
atp, keys->sk_argument);
|
|
|
|
if (!test == !(keys->sk_flags & SK_NEGATE))
|
|
return false;
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
/* ----------------
|
|
* heap_tuple_satisfies
|
|
*
|
|
* Returns a valid HeapTuple if it satisfies the timequal and keytest.
|
|
* Returns NULL otherwise. Used to be heap_satisifies (sic) which
|
|
* returned a boolean. It now returns a tuple so that we can avoid doing two
|
|
* PageGetItem's per tuple.
|
|
*
|
|
* Complete check of validity including LP_CTUP and keytest.
|
|
* This should perhaps be combined with valid somehow in the
|
|
* future. (Also, additional rule tests/time range tests.)
|
|
*
|
|
* on 8/21/92 mao says: i rearranged the tests here to do keytest before
|
|
* SatisfiesTimeQual. profiling indicated that even for vacuumed relations,
|
|
* time qual checking was more expensive than key testing. time qual is
|
|
* least likely to fail, too. we should really add the time qual test to
|
|
* the restriction and optimize it in the normal way. this has interactions
|
|
* with joey's expensive function work.
|
|
* ----------------
|
|
*/
|
|
HeapTuple
|
|
heap_tuple_satisfies(ItemId itemId,
|
|
Relation relation,
|
|
Buffer buffer,
|
|
PageHeader disk_page,
|
|
TimeQual qual,
|
|
int nKeys,
|
|
ScanKey key)
|
|
{
|
|
HeapTuple tuple, result;
|
|
bool res;
|
|
TransactionId old_tmin, old_tmax;
|
|
|
|
if (! ItemIdIsUsed(itemId))
|
|
return NULL;
|
|
|
|
tuple = (HeapTuple) PageGetItem((Page) disk_page, itemId);
|
|
|
|
if (key != NULL)
|
|
res = heap_keytest(tuple, RelationGetTupleDescriptor(relation),
|
|
nKeys, key);
|
|
else
|
|
res = TRUE;
|
|
|
|
result = (HeapTuple)NULL;
|
|
if (res) {
|
|
if(relation->rd_rel->relkind == RELKIND_UNCATALOGED) {
|
|
result = tuple;
|
|
} else {
|
|
old_tmin = tuple->t_tmin;
|
|
old_tmax = tuple->t_tmax;
|
|
res = HeapTupleSatisfiesTimeQual(tuple,qual);
|
|
if(tuple->t_tmin != old_tmin ||
|
|
tuple->t_tmax != old_tmax) {
|
|
SetBufferCommitInfoNeedsSave(buffer);
|
|
}
|
|
if(res) {
|
|
result = tuple;
|
|
}
|
|
}
|
|
}
|
|
|
|
return result;
|
|
}
|
|
|
|
/*
|
|
* TupleUpdatedByCurXactAndCmd() -- Returns true if this tuple has
|
|
* already been updated once by the current transaction/command
|
|
* pair.
|
|
*/
|
|
bool
|
|
TupleUpdatedByCurXactAndCmd(HeapTuple t)
|
|
{
|
|
if (TransactionIdEquals(t->t_xmax,
|
|
GetCurrentTransactionId()) &&
|
|
t->t_cmax == GetCurrentCommandId())
|
|
return true;
|
|
|
|
return false;
|
|
}
|