@ -907,7 +907,6 @@ _bt_first(IndexScanDesc scan, ScanDirection dir)
*/ */
if ( ! so - > qual_ok ) if ( ! so - > qual_ok )
{ {
/* Notify any other workers that we're done with this scan key. */
_bt_parallel_done ( scan ) ; _bt_parallel_done ( scan ) ;
return false ; return false ;
} }
@ -917,10 +916,22 @@ _bt_first(IndexScanDesc scan, ScanDirection dir)
* scan has not started , proceed to find out first leaf page in the usual * scan has not started , proceed to find out first leaf page in the usual
* way while keeping other participating processes waiting . If the scan * way while keeping other participating processes waiting . If the scan
* has already begun , use the page number from the shared structure . * has already begun , use the page number from the shared structure .
*
* When a parallel scan has another primitive index scan scheduled , a
* parallel worker will seize the scan for that purpose now . This is
* similar to the case where the top - level scan hasn ' t started .
*/ */
if ( scan - > parallel_scan ! = NULL ) if ( scan - > parallel_scan ! = NULL )
{ {
status = _bt_parallel_seize ( scan , & blkno ) ; status = _bt_parallel_seize ( scan , & blkno , true ) ;
/*
* Initialize arrays ( when _bt_parallel_seize didn ' t already set up
* the next primitive index scan )
*/
if ( so - > numArrayKeys & & ! so - > needPrimScan )
_bt_start_array_keys ( scan , dir ) ;
if ( ! status ) if ( ! status )
return false ; return false ;
else if ( blkno = = P_NONE ) else if ( blkno = = P_NONE )
@ -935,6 +946,16 @@ _bt_first(IndexScanDesc scan, ScanDirection dir)
goto readcomplete ; goto readcomplete ;
} }
} }
else if ( so - > numArrayKeys & & ! so - > needPrimScan )
{
/*
* First _bt_first call ( for current btrescan ) without parallelism .
*
* Initialize arrays , and the corresponding scan keys that were just
* output by _bt_preprocess_keys .
*/
_bt_start_array_keys ( scan , dir ) ;
}
/*----------
/*----------
* Examine the scan keys to discover where we need to start the scan . * Examine the scan keys to discover where we need to start the scan .
@ -980,6 +1001,18 @@ _bt_first(IndexScanDesc scan, ScanDirection dir)
* *
* The selected scan keys ( at most one per index column ) are remembered by * The selected scan keys ( at most one per index column ) are remembered by
* storing their addresses into the local startKeys [ ] array . * storing their addresses into the local startKeys [ ] array .
*
* _bt_checkkeys / _bt_advance_array_keys decide whether and when to start
* the next primitive index scan ( for scans with array keys ) based in part
* on an understanding of how it ' ll enable us to reposition the scan .
* They ' re directly aware of how we ' ll sometimes cons up an explicit
* SK_SEARCHNOTNULL key . They ' ll even end primitive scans by applying a
* symmetric " deduce NOT NULL " rule of their own . This allows top - level
* scans to skip large groups of NULLs through repeated deductions about
* key strictness ( for a required inequality key ) and whether NULLs in the
* key ' s index column are stored last or first ( relative to non - NULLs ) .
* If you update anything here , _bt_checkkeys / _bt_advance_array_keys might
* need to be kept in sync .
* - - - - - - - - - - * - - - - - - - - - -
*/ */
strat_total = BTEqualStrategyNumber ; strat_total = BTEqualStrategyNumber ;
@ -1502,7 +1535,8 @@ _bt_next(IndexScanDesc scan, ScanDirection dir)
* We scan the current page starting at offnum and moving in the indicated * We scan the current page starting at offnum and moving in the indicated
* direction . All items matching the scan keys are loaded into currPos . items . * direction . All items matching the scan keys are loaded into currPos . items .
* moreLeft or moreRight ( as appropriate ) is cleared if _bt_checkkeys reports * moreLeft or moreRight ( as appropriate ) is cleared if _bt_checkkeys reports
* that there can be no more matching tuples in the current scan direction . * that there can be no more matching tuples in the current scan direction
* ( could just be for the current primitive index scan when scan has arrays ) .
* *
* _bt_first caller passes us an offnum returned by _bt_binsrch , which might * _bt_first caller passes us an offnum returned by _bt_binsrch , which might
* be an out of bounds offnum such as " maxoff + 1 " in certain corner cases . * be an out of bounds offnum such as " maxoff + 1 " in certain corner cases .
@ -1527,11 +1561,10 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum,
BTPageOpaque opaque ; BTPageOpaque opaque ;
OffsetNumber minoff ; OffsetNumber minoff ;
OffsetNumber maxoff ; OffsetNumber maxoff ;
int itemIndex ; BTReadPageState pstate ;
bool continuescan ; bool arrayKeys ;
int indnatts ; int itemIndex ,
bool continuescanPrechecked ; indnatts ;
bool haveFirstMatch = false ;
/*
/*
* We must have the buffer pinned and locked , but the usual macro can ' t be * We must have the buffer pinned and locked , but the usual macro can ' t be
@ -1546,16 +1579,32 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum,
if ( scan - > parallel_scan ) if ( scan - > parallel_scan )
{ {
if ( ScanDirectionIsForward ( dir ) ) if ( ScanDirectionIsForward ( dir ) )
_bt_parallel_release ( scan , opaque - > btpo_next ) ; pstate . prev_scan_page = opaque - > btpo_next ;
else else
_bt_parallel_release ( scan , BufferGetBlockNumber ( so - > currPos . buf ) ) ; pstate . prev_scan_page = BufferGetBlockNumber ( so - > currPos . buf ) ;
_bt_parallel_release ( scan , pstate . prev_scan_page ) ;
} }
continuescan = true ; /* default assumption */
indnatts = IndexRelationGetNumberOfAttributes ( scan - > indexRelation ) ; indnatts = IndexRelationGetNumberOfAttributes ( scan - > indexRelation ) ;
arrayKeys = so - > numArrayKeys ! = 0 ;
minoff = P_FIRSTDATAKEY ( opaque ) ; minoff = P_FIRSTDATAKEY ( opaque ) ;
maxoff = PageGetMaxOffsetNumber ( page ) ; maxoff = PageGetMaxOffsetNumber ( page ) ;
/* initialize page-level state that we'll pass to _bt_checkkeys */
pstate . dir = dir ;
pstate . minoff = minoff ;
pstate . maxoff = maxoff ;
pstate . finaltup = NULL ;
pstate . page = page ;
pstate . offnum = InvalidOffsetNumber ;
pstate . skip = InvalidOffsetNumber ;
pstate . continuescan = true ; /* default assumption */
pstate . prechecked = false ;
pstate . firstmatch = false ;
pstate . rechecks = 0 ;
pstate . targetdistance = 0 ;
/*
/*
* We note the buffer ' s block number so that we can release the pin later . * We note the buffer ' s block number so that we can release the pin later .
* This allows us to re - read the buffer if it is needed again for hinting . * This allows us to re - read the buffer if it is needed again for hinting .
@ -1598,10 +1647,34 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum,
* corresponding value from the last item on the page . So checking with * corresponding value from the last item on the page . So checking with
* the last item on the page would give a more precise answer . * the last item on the page would give a more precise answer .
* *
* We skip this for the first page in the scan to evade the possible * We skip this for the first page read by each ( primitive ) scan , to avoid
* slowdown of the point queries . * slowing down point queries . They typically don ' t stand to gain much
* when the optimization can be applied , and are more likely to notice the
* overhead of the precheck .
*
* The optimization is unsafe and must be avoided whenever _bt_checkkeys
* just set a low - order required array ' s key to the best available match
* for a truncated - inf attribute value from the prior page ' s high key
* ( array element 0 is always the best available match in this scenario ) .
* It ' s quite likely that matches for array element 0 begin on this page ,
* but the start of matches won ' t necessarily align with page boundaries .
* When the start of matches is somewhere in the middle of this page , it
* would be wrong to treat page ' s final non - pivot tuple as representative .
* Doing so might lead us to treat some of the page ' s earlier tuples as
* being part of a group of tuples thought to satisfy the required keys .
*
* Note : Conversely , in the case where the scan ' s arrays just advanced
* using the prior page ' s HIKEY _without_ advancement setting scanBehind ,
* the start of matches must be aligned with page boundaries , which makes
* it safe to attempt the optimization here now . It ' s also safe when the
* prior page ' s HIKEY simply didn ' t need to advance any required array . In
* both cases we can safely assume that the _first_ tuple from this page
* must be > = the current set of array keys / equality constraints . And so
* if the final tuple is = = those same keys ( and also satisfies any
* required < or < = strategy scan keys ) during the precheck , we can safely
* assume that this must also be true of all earlier tuples from the page .
*/ */
if ( ! firstPage & & minoff < maxoff ) if ( ! firstPage & & ! so - > scanBehind & & minoff < maxoff )
{ {
ItemId iid ; ItemId iid ;
IndexTuple itup ; IndexTuple itup ;
@ -1609,22 +1682,22 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum,
iid = PageGetItemId ( page , ScanDirectionIsForward ( dir ) ? maxoff : minoff ) ; iid = PageGetItemId ( page , ScanDirectionIsForward ( dir ) ? maxoff : minoff ) ;
itup = ( IndexTuple ) PageGetItem ( page , iid ) ; itup = ( IndexTuple ) PageGetItem ( page , iid ) ;
/*
/* Call with arrayKeys=false to avoid undesirable side-effects */
* Do the precheck . Note that we pass the pointer to the _bt_checkkeys ( scan , & pstate , false , itup , indnatts ) ;
* ' continuescanPrechecked ' to the ' continuescan ' argument . That will pstate . prechecked = pstate . continuescan ;
* set flag to true if all required keys are satisfied and false pstate . continuescan = true ; /* reset */
* otherwise .
*/
( void ) _bt_checkkeys ( scan , itup , indnatts , dir ,
& continuescanPrechecked , false , false ) ;
}
else
{
continuescanPrechecked = false ;
} }
if ( ScanDirectionIsForward ( dir ) ) if ( ScanDirectionIsForward ( dir ) )
{ {
/* SK_SEARCHARRAY forward scans must provide high key up front */
if ( arrayKeys & & ! P_RIGHTMOST ( opaque ) )
{
ItemId iid = PageGetItemId ( page , P_HIKEY ) ;
pstate . finaltup = ( IndexTuple ) PageGetItem ( page , iid ) ;
}
/* load items[] in ascending order */ /* load items[] in ascending order */
itemIndex = 0 ; itemIndex = 0 ;
@ -1649,23 +1722,28 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum,
itup = ( IndexTuple ) PageGetItem ( page , iid ) ; itup = ( IndexTuple ) PageGetItem ( page , iid ) ;
Assert ( ! BTreeTupleIsPivot ( itup ) ) ; Assert ( ! BTreeTupleIsPivot ( itup ) ) ;
passes_quals = _bt_checkkeys ( scan , itup , indnatts , dir , pstate . offnum = offnum ;
& continuescan , passes_quals = _bt_checkkeys ( scan , & pstate , arrayKeys ,
continuescanPrechecked , itup , indnatts ) ;
haveFirstMatch ) ;
/*
/*
* If the result of prechecking required keys was true , then in * Check if we need to skip ahead to a later tuple ( only possible
* assert - enabled builds we also recheck that the _bt_checkkeys ( ) * when the scan uses array keys )
* result is the same .
*/ */
Assert ( ( ! continuescanPrechecked & & haveFirstMatch ) | | if ( arrayKeys & & OffsetNumberIsValid ( pstate . skip ) )
passes_quals = = _bt_checkkeys ( scan , itup , indnatts , dir , {
& continuescan , false , false ) ) ; Assert ( ! passes_quals & & pstate . continuescan ) ;
Assert ( offnum < pstate . skip ) ;
offnum = pstate . skip ;
pstate . skip = InvalidOffsetNumber ;
continue ;
}
if ( passes_quals ) if ( passes_quals )
{ {
/* tuple passes all scan key conditions */ /* tuple passes all scan key conditions */
haveFirstMatch = true ; pstate . firstm atch= true ;
if ( ! BTreeTupleIsPosting ( itup ) ) if ( ! BTreeTupleIsPosting ( itup ) )
{ {
/* Remember it */ /* Remember it */
@ -1696,7 +1774,7 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum,
} }
} }
/* When !continuescan, there can't be any more matches, so stop */ /* When !continuescan, there can't be any more matches, so stop */
if ( ! continuescan ) if ( ! pstate . continuescan )
break ; break ;
offnum = OffsetNumberNext ( offnum ) ; offnum = OffsetNumberNext ( offnum ) ;
@ -1713,17 +1791,18 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum,
* only appear on non - pivot tuples on the right sibling page are * only appear on non - pivot tuples on the right sibling page are
* common . * common .
*/ */
if ( continuescan & & ! P_RIGHTMOST ( opaque ) ) if ( pstate . continuescan & & ! P_RIGHTMOST ( opaque ) )
{ {
ItemId iid = PageGetItemId ( page , P_HIKEY ) ; ItemId iid = PageGetItemId ( page , P_HIKEY ) ;
IndexTuple itup = ( IndexTuple ) PageGetItem ( page , iid ) ; IndexTuple itup = ( IndexTuple ) PageGetItem ( page , iid ) ;
int truncatt ; int truncatt ;
truncatt = BTreeTupleGetNAtts ( itup , scan - > indexRelation ) ; truncatt = BTreeTupleGetNAtts ( itup , scan - > indexRelation ) ;
_bt_checkkeys ( scan , itup , truncatt , dir , & continuescan , false , false ) ; pstate . prechecked = false ; /* precheck didn't cover HIKEY */
_bt_checkkeys ( scan , & pstate , arrayKeys , itup , truncatt ) ;
} }
if ( ! continuescan ) if ( ! pstate . continuescan )
so - > currPos . moreRight = false ; so - > currPos . moreRight = false ;
Assert ( itemIndex < = MaxTIDsPerBTreePage ) ; Assert ( itemIndex < = MaxTIDsPerBTreePage ) ;
@ -1733,6 +1812,14 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum,
} }
else else
{ {
/* SK_SEARCHARRAY backward scans must provide final tuple up front */
if ( arrayKeys & & minoff < = maxoff & & ! P_LEFTMOST ( opaque ) )
{
ItemId iid = PageGetItemId ( page , minoff ) ;
pstate . finaltup = ( IndexTuple ) PageGetItem ( page , iid ) ;
}
/* load items[] in descending order */ /* load items[] in descending order */
itemIndex = MaxTIDsPerBTreePage ; itemIndex = MaxTIDsPerBTreePage ;
@ -1772,23 +1859,28 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum,
itup = ( IndexTuple ) PageGetItem ( page , iid ) ; itup = ( IndexTuple ) PageGetItem ( page , iid ) ;
Assert ( ! BTreeTupleIsPivot ( itup ) ) ; Assert ( ! BTreeTupleIsPivot ( itup ) ) ;
passes_quals = _bt_checkkeys ( scan , itup , indnatts , dir , pstate . offnum = offnum ;
& continuescan , passes_quals = _bt_checkkeys ( scan , & pstate , arrayKeys ,
continuescanPrechecked , itup , indnatts ) ;
haveFirstMatch ) ;
/*
/*
* If the result of prechecking required keys was true , then in * Check if we need to skip ahead to a later tuple ( only possible
* assert - enabled builds we also recheck that the _bt_checkkeys ( ) * when the scan uses array keys )
* result is the same .
*/ */
Assert ( ( ! continuescanPrechecked & & ! haveFirstMatch ) | | if ( arrayKeys & & OffsetNumberIsValid ( pstate . skip ) )
passes_quals = = _bt_checkkeys ( scan , itup , indnatts , dir , {
& continuescan , false , false ) ) ; Assert ( ! passes_quals & & pstate . continuescan ) ;
Assert ( offnum > pstate . skip ) ;
offnum = pstate . skip ;
pstate . skip = InvalidOffsetNumber ;
continue ;
}
if ( passes_quals & & tuple_alive ) if ( passes_quals & & tuple_alive )
{ {
/* tuple passes all scan key conditions */ /* tuple passes all scan key conditions */
haveFirstMatch = true ; pstate . firstm atch= true ;
if ( ! BTreeTupleIsPosting ( itup ) ) if ( ! BTreeTupleIsPosting ( itup ) )
{ {
/* Remember it */ /* Remember it */
@ -1824,7 +1916,7 @@ _bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum,
} }
} }
} }
if ( ! continuescan ) if ( ! pstate . continuescan )
{ {
/* there can't be any more matches, so stop */ /* there can't be any more matches, so stop */
so - > currPos . moreLeft = false ; so - > currPos . moreLeft = false ;
@ -1970,6 +2062,31 @@ _bt_steppage(IndexScanDesc scan, ScanDirection dir)
so - > currPos . nextTupleOffset ) ; so - > currPos . nextTupleOffset ) ;
so - > markPos . itemIndex = so - > markItemIndex ; so - > markPos . itemIndex = so - > markItemIndex ;
so - > markItemIndex = - 1 ; so - > markItemIndex = - 1 ;
/*
* If we ' re just about to start the next primitive index scan
* ( possible with a scan that has arrays keys , and needs to skip to
* continue in the current scan direction ) , moreLeft / moreRight only
* indicate the end of the current primitive index scan . They must
* never be taken to indicate that the top - level index scan has ended
* ( that would be wrong ) .
*
* We could handle this case by treating the current array keys as
* markPos state . But depending on the current array state like this
* would add complexity . Instead , we just unset markPos ' s copy of
* moreRight or moreLeft ( whichever might be affected ) , while making
* btrestpos reset the scan ' s arrays to their initial scan positions .
* In effect , btrestpos leaves advancing the arrays up to the first
* _bt_readpage call ( that takes place after it has restored markPos ) .
*/
Assert ( so - > markPos . dir = = dir ) ;
if ( so - > needPrimScan )
{
if ( ScanDirectionIsForward ( dir ) )
so - > markPos . moreRight = true ;
else
so - > markPos . moreLeft = true ;
}
} }
if ( ScanDirectionIsForward ( dir ) ) if ( ScanDirectionIsForward ( dir ) )
@ -1981,7 +2098,7 @@ _bt_steppage(IndexScanDesc scan, ScanDirection dir)
* Seize the scan to get the next block number ; if the scan has * Seize the scan to get the next block number ; if the scan has
* ended already , bail out . * ended already , bail out .
*/ */
status = _bt_parallel_seize ( scan , & blkno ) ; status = _bt_parallel_seize ( scan , & blkno , false ) ;
if ( ! status ) if ( ! status )
{ {
/* release the previous buffer, if pinned */ /* release the previous buffer, if pinned */
@ -2013,7 +2130,7 @@ _bt_steppage(IndexScanDesc scan, ScanDirection dir)
* Seize the scan to get the current block number ; if the scan has * Seize the scan to get the current block number ; if the scan has
* ended already , bail out . * ended already , bail out .
*/ */
status = _bt_parallel_seize ( scan , & blkno ) ; status = _bt_parallel_seize ( scan , & blkno , false ) ;
BTScanPosUnpinIfPinned ( so - > currPos ) ; BTScanPosUnpinIfPinned ( so - > currPos ) ;
if ( ! status ) if ( ! status )
{ {
@ -2097,7 +2214,7 @@ _bt_readnextpage(IndexScanDesc scan, BlockNumber blkno, ScanDirection dir)
if ( scan - > parallel_scan ! = NULL ) if ( scan - > parallel_scan ! = NULL )
{ {
_bt_relbuf ( rel , so - > currPos . buf ) ; _bt_relbuf ( rel , so - > currPos . buf ) ;
status = _bt_parallel_seize ( scan , & blkno ) ; status = _bt_parallel_seize ( scan , & blkno , false ) ;
if ( ! status ) if ( ! status )
{ {
BTScanPosInvalidate ( so - > currPos ) ; BTScanPosInvalidate ( so - > currPos ) ;
@ -2193,7 +2310,7 @@ _bt_readnextpage(IndexScanDesc scan, BlockNumber blkno, ScanDirection dir)
if ( scan - > parallel_scan ! = NULL ) if ( scan - > parallel_scan ! = NULL )
{ {
_bt_relbuf ( rel , so - > currPos . buf ) ; _bt_relbuf ( rel , so - > currPos . buf ) ;
status = _bt_parallel_seize ( scan , & blkno ) ; status = _bt_parallel_seize ( scan , & blkno , false ) ;
if ( ! status ) if ( ! status )
{ {
BTScanPosInvalidate ( so - > currPos ) ; BTScanPosInvalidate ( so - > currPos ) ;
@ -2218,6 +2335,8 @@ _bt_parallel_readpage(IndexScanDesc scan, BlockNumber blkno, ScanDirection dir)
{ {
BTScanOpaque so = ( BTScanOpaque ) scan - > opaque ; BTScanOpaque so = ( BTScanOpaque ) scan - > opaque ;
Assert ( ! so - > needPrimScan ) ;
_bt_initialize_more_data ( so , dir ) ; _bt_initialize_more_data ( so , dir ) ;
if ( ! _bt_readnextpage ( scan , blkno , dir ) ) if ( ! _bt_readnextpage ( scan , blkno , dir ) )
@ -2524,14 +2643,22 @@ _bt_endpoint(IndexScanDesc scan, ScanDirection dir)
} }
/*
/*
* _bt_initialize_more_data ( ) - - initialize moreLeft / moreRight appropriately * _bt_initialize_more_data ( ) - - initialize moreLeft , moreRight and scan dir
* for scan direction * from currPos
*/ */
static inline void static inline void
_bt_initialize_more_data ( BTScanOpaque so , ScanDirection dir ) _bt_initialize_more_data ( BTScanOpaque so , ScanDirection dir )
{ {
/* initialize moreLeft/moreRight appropriately for scan direction */ so - > currPos . dir = dir ;
if ( ScanDirectionIsForward ( dir ) ) if ( so - > needPrimScan )
{
Assert ( so - > numArrayKeys ) ;
so - > currPos . moreLeft = true ;
so - > currPos . moreRight = true ;
so - > needPrimScan = false ;
}
else if ( ScanDirectionIsForward ( dir ) )
{ {
so - > currPos . moreLeft = false ; so - > currPos . moreLeft = false ;
so - > currPos . moreRight = true ; so - > currPos . moreRight = true ;
Peter Geoghegan
2 years ago