mirror of
https://github.com/postgres/postgres.git
synced 2025-07-02 09:02:37 +03:00
Predicate locking in GIN index
Predicate locks are used on per page basis only if fastupdate = off, in opposite case predicate lock on pending list will effectively lock whole index, to reduce locking overhead, just lock a relation. Entry and posting trees are essentially B-tree, so locks are acquired on leaf pages only. Author: Shubham Barai with some editorization by me and Dmitry Ivanov Review by: Alexander Korotkov, Dmitry Ivanov, Fedor Sigaev Discussion: https://www.postgresql.org/message-id/flat/CALxAEPt5sWW+EwTaKUGFL5_XFcZ0MuGBcyJ70oqbWqr42YKR8Q@mail.gmail.com
This commit is contained in:
@ -17,6 +17,7 @@
|
||||
#include "access/gin_private.h"
|
||||
#include "access/ginxlog.h"
|
||||
#include "access/xloginsert.h"
|
||||
#include "storage/predicate.h"
|
||||
#include "miscadmin.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "utils/rel.h"
|
||||
@ -515,6 +516,19 @@ ginPlaceToPage(GinBtree btree, GinBtreeStack *stack,
|
||||
btree->fillRoot(btree, newrootpg,
|
||||
BufferGetBlockNumber(lbuffer), newlpage,
|
||||
BufferGetBlockNumber(rbuffer), newrpage);
|
||||
|
||||
if (GinPageIsLeaf(BufferGetPage(stack->buffer)))
|
||||
{
|
||||
|
||||
PredicateLockPageSplit(btree->index,
|
||||
BufferGetBlockNumber(stack->buffer),
|
||||
BufferGetBlockNumber(lbuffer));
|
||||
|
||||
PredicateLockPageSplit(btree->index,
|
||||
BufferGetBlockNumber(stack->buffer),
|
||||
BufferGetBlockNumber(rbuffer));
|
||||
}
|
||||
|
||||
}
|
||||
else
|
||||
{
|
||||
@ -524,6 +538,14 @@ ginPlaceToPage(GinBtree btree, GinBtreeStack *stack,
|
||||
GinPageGetOpaque(newrpage)->rightlink = savedRightLink;
|
||||
GinPageGetOpaque(newlpage)->flags |= GIN_INCOMPLETE_SPLIT;
|
||||
GinPageGetOpaque(newlpage)->rightlink = BufferGetBlockNumber(rbuffer);
|
||||
|
||||
if (GinPageIsLeaf(BufferGetPage(stack->buffer)))
|
||||
{
|
||||
|
||||
PredicateLockPageSplit(btree->index,
|
||||
BufferGetBlockNumber(stack->buffer),
|
||||
BufferGetBlockNumber(rbuffer));
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
|
@ -19,6 +19,7 @@
|
||||
#include "access/xloginsert.h"
|
||||
#include "lib/ilist.h"
|
||||
#include "miscadmin.h"
|
||||
#include "storage/predicate.h"
|
||||
#include "utils/rel.h"
|
||||
|
||||
/*
|
||||
@ -1759,7 +1760,7 @@ leafRepackItems(disassembledLeaf *leaf, ItemPointer remaining)
|
||||
*/
|
||||
BlockNumber
|
||||
createPostingTree(Relation index, ItemPointerData *items, uint32 nitems,
|
||||
GinStatsData *buildStats)
|
||||
GinStatsData *buildStats, Buffer entrybuffer)
|
||||
{
|
||||
BlockNumber blkno;
|
||||
Buffer buffer;
|
||||
@ -1810,6 +1811,12 @@ createPostingTree(Relation index, ItemPointerData *items, uint32 nitems,
|
||||
page = BufferGetPage(buffer);
|
||||
blkno = BufferGetBlockNumber(buffer);
|
||||
|
||||
/*
|
||||
* Copy a predicate lock from entry tree leaf (containing posting list)
|
||||
* to posting tree.
|
||||
*/
|
||||
PredicateLockPageSplit(index, BufferGetBlockNumber(entrybuffer), blkno);
|
||||
|
||||
START_CRIT_SECTION();
|
||||
|
||||
PageRestoreTempPage(tmppage, page);
|
||||
@ -1904,6 +1911,7 @@ ginInsertItemPointers(Relation index, BlockNumber rootBlkno,
|
||||
btree.itemptr = insertdata.items[insertdata.curitem];
|
||||
stack = ginFindLeafPage(&btree, false, NULL);
|
||||
|
||||
GinCheckForSerializableConflictIn(btree.index, NULL, stack->buffer);
|
||||
ginInsertValue(&btree, stack, &insertdata, buildStats);
|
||||
}
|
||||
}
|
||||
|
@ -17,8 +17,10 @@
|
||||
#include "access/gin_private.h"
|
||||
#include "access/relscan.h"
|
||||
#include "miscadmin.h"
|
||||
#include "storage/predicate.h"
|
||||
#include "utils/datum.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "utils/rel.h"
|
||||
|
||||
/* GUC parameter */
|
||||
int GinFuzzySearchLimit = 0;
|
||||
@ -33,11 +35,25 @@ typedef struct pendingPosition
|
||||
} pendingPosition;
|
||||
|
||||
|
||||
/*
|
||||
* Place predicate lock on GIN page if needed.
|
||||
*/
|
||||
static void
|
||||
GinPredicateLockPage(Relation index, BlockNumber blkno, Snapshot snapshot)
|
||||
{
|
||||
/*
|
||||
* When fast update is on then no need in locking pages, because we
|
||||
* anyway need to lock the whole index.
|
||||
*/
|
||||
if (!GinGetUseFastUpdate(index))
|
||||
PredicateLockPage(index, blkno, snapshot);
|
||||
}
|
||||
|
||||
/*
|
||||
* Goes to the next page if current offset is outside of bounds
|
||||
*/
|
||||
static bool
|
||||
moveRightIfItNeeded(GinBtreeData *btree, GinBtreeStack *stack)
|
||||
moveRightIfItNeeded(GinBtreeData *btree, GinBtreeStack *stack, Snapshot snapshot)
|
||||
{
|
||||
Page page = BufferGetPage(stack->buffer);
|
||||
|
||||
@ -52,6 +68,7 @@ moveRightIfItNeeded(GinBtreeData *btree, GinBtreeStack *stack)
|
||||
stack->buffer = ginStepRight(stack->buffer, btree->index, GIN_SHARE);
|
||||
stack->blkno = BufferGetBlockNumber(stack->buffer);
|
||||
stack->off = FirstOffsetNumber;
|
||||
GinPredicateLockPage(btree->index, stack->blkno, snapshot);
|
||||
}
|
||||
|
||||
return true;
|
||||
@ -73,6 +90,7 @@ scanPostingTree(Relation index, GinScanEntry scanEntry,
|
||||
/* Descend to the leftmost leaf page */
|
||||
stack = ginScanBeginPostingTree(&btree, index, rootPostingTree, snapshot);
|
||||
buffer = stack->buffer;
|
||||
|
||||
IncrBufferRefCount(buffer); /* prevent unpin in freeGinBtreeStack */
|
||||
|
||||
freeGinBtreeStack(stack);
|
||||
@ -82,6 +100,11 @@ scanPostingTree(Relation index, GinScanEntry scanEntry,
|
||||
*/
|
||||
for (;;)
|
||||
{
|
||||
/*
|
||||
* Predicate lock each leaf page in posting tree
|
||||
*/
|
||||
GinPredicateLockPage(index, BufferGetBlockNumber(buffer), snapshot);
|
||||
|
||||
page = BufferGetPage(buffer);
|
||||
if ((GinPageGetOpaque(page)->flags & GIN_DELETED) == 0)
|
||||
{
|
||||
@ -131,6 +154,12 @@ collectMatchBitmap(GinBtreeData *btree, GinBtreeStack *stack,
|
||||
attnum = scanEntry->attnum;
|
||||
attr = TupleDescAttr(btree->ginstate->origTupdesc, attnum - 1);
|
||||
|
||||
/*
|
||||
* Predicate lock entry leaf page, following pages will be locked by
|
||||
* moveRightIfItNeeded()
|
||||
*/
|
||||
GinPredicateLockPage(btree->index, stack->buffer, snapshot);
|
||||
|
||||
for (;;)
|
||||
{
|
||||
Page page;
|
||||
@ -141,7 +170,7 @@ collectMatchBitmap(GinBtreeData *btree, GinBtreeStack *stack,
|
||||
/*
|
||||
* stack->off points to the interested entry, buffer is already locked
|
||||
*/
|
||||
if (moveRightIfItNeeded(btree, stack) == false)
|
||||
if (moveRightIfItNeeded(btree, stack, snapshot) == false)
|
||||
return true;
|
||||
|
||||
page = BufferGetPage(stack->buffer);
|
||||
@ -250,7 +279,7 @@ collectMatchBitmap(GinBtreeData *btree, GinBtreeStack *stack,
|
||||
Datum newDatum;
|
||||
GinNullCategory newCategory;
|
||||
|
||||
if (moveRightIfItNeeded(btree, stack) == false)
|
||||
if (moveRightIfItNeeded(btree, stack, snapshot) == false)
|
||||
elog(ERROR, "lost saved point in index"); /* must not happen !!! */
|
||||
|
||||
page = BufferGetPage(stack->buffer);
|
||||
@ -323,6 +352,7 @@ restartScanEntry:
|
||||
ginstate);
|
||||
stackEntry = ginFindLeafPage(&btreeEntry, true, snapshot);
|
||||
page = BufferGetPage(stackEntry->buffer);
|
||||
|
||||
/* ginFindLeafPage() will have already checked snapshot age. */
|
||||
needUnlock = true;
|
||||
|
||||
@ -370,6 +400,10 @@ restartScanEntry:
|
||||
{
|
||||
IndexTuple itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, stackEntry->off));
|
||||
|
||||
/* Predicate lock visited entry leaf page */
|
||||
GinPredicateLockPage(ginstate->index,
|
||||
BufferGetBlockNumber(stackEntry->buffer), snapshot);
|
||||
|
||||
if (GinIsPostingTree(itup))
|
||||
{
|
||||
BlockNumber rootPostingTree = GinGetPostingTree(itup);
|
||||
@ -391,6 +425,12 @@ restartScanEntry:
|
||||
rootPostingTree, snapshot);
|
||||
entry->buffer = stack->buffer;
|
||||
|
||||
/*
|
||||
* Predicate lock visited posting tree page, following pages
|
||||
* will be locked by moveRightIfItNeeded or entryLoadMoreItems
|
||||
*/
|
||||
GinPredicateLockPage(ginstate->index, BufferGetBlockNumber(entry->buffer), snapshot);
|
||||
|
||||
/*
|
||||
* We keep buffer pinned because we need to prevent deletion of
|
||||
* page during scan. See GIN's vacuum implementation. RefCount is
|
||||
@ -493,7 +533,7 @@ startScanKey(GinState *ginstate, GinScanOpaque so, GinScanKey key)
|
||||
|
||||
for (i = 0; i < key->nentries - 1; i++)
|
||||
{
|
||||
/* Pass all entries <= i as FALSE, and the rest as MAYBE */
|
||||
/* Pass all entries <= i as false, and the rest as MAYBE */
|
||||
for (j = 0; j <= i; j++)
|
||||
key->entryRes[entryIndexes[j]] = GIN_FALSE;
|
||||
for (j = i + 1; j < key->nentries; j++)
|
||||
@ -633,6 +673,8 @@ entryLoadMoreItems(GinState *ginstate, GinScanEntry entry,
|
||||
entry->btree.fullScan = false;
|
||||
stack = ginFindLeafPage(&entry->btree, true, snapshot);
|
||||
|
||||
GinPredicateLockPage(ginstate->index, BufferGetBlockNumber(stack->buffer), snapshot);
|
||||
|
||||
/* we don't need the stack, just the buffer. */
|
||||
entry->buffer = stack->buffer;
|
||||
IncrBufferRefCount(entry->buffer);
|
||||
@ -677,6 +719,10 @@ entryLoadMoreItems(GinState *ginstate, GinScanEntry entry,
|
||||
entry->buffer = ginStepRight(entry->buffer,
|
||||
ginstate->index,
|
||||
GIN_SHARE);
|
||||
|
||||
GinPredicateLockPage(ginstate->index, BufferGetBlockNumber(entry->buffer), snapshot);
|
||||
|
||||
|
||||
page = BufferGetPage(entry->buffer);
|
||||
}
|
||||
stepright = true;
|
||||
@ -1038,8 +1084,8 @@ keyGetItem(GinState *ginstate, MemoryContext tempCtx, GinScanKey key,
|
||||
* lossy page even when none of the other entries match.
|
||||
*
|
||||
* Our strategy is to call the tri-state consistent function, with the
|
||||
* lossy-page entries set to MAYBE, and all the other entries FALSE. If it
|
||||
* returns FALSE, none of the lossy items alone are enough for a match, so
|
||||
* lossy-page entries set to MAYBE, and all the other entries false. If it
|
||||
* returns false, none of the lossy items alone are enough for a match, so
|
||||
* we don't need to return a lossy-page pointer. Otherwise, return a
|
||||
* lossy-page pointer to indicate that the whole heap page must be
|
||||
* checked. (On subsequent calls, we'll do nothing until minItem is past
|
||||
@ -1700,7 +1746,8 @@ collectMatchesForHeapRow(IndexScanDesc scan, pendingPosition *pos)
|
||||
}
|
||||
|
||||
/*
|
||||
* Collect all matched rows from pending list into bitmap
|
||||
* Collect all matched rows from pending list into bitmap. Also function
|
||||
* takes PendingLockRelation if it's needed.
|
||||
*/
|
||||
static void
|
||||
scanPendingInsert(IndexScanDesc scan, TIDBitmap *tbm, int64 *ntids)
|
||||
@ -1730,9 +1777,24 @@ scanPendingInsert(IndexScanDesc scan, TIDBitmap *tbm, int64 *ntids)
|
||||
{
|
||||
/* No pending list, so proceed with normal scan */
|
||||
UnlockReleaseBuffer(metabuffer);
|
||||
|
||||
/*
|
||||
* If fast update is enabled, we acquire a predicate lock on the entire
|
||||
* relation as fast update postpones the insertion of tuples into index
|
||||
* structure due to which we can't detect rw conflicts.
|
||||
*/
|
||||
if (GinGetUseFastUpdate(scan->indexRelation))
|
||||
PredicateLockRelation(scan->indexRelation, scan->xs_snapshot);
|
||||
|
||||
return;
|
||||
}
|
||||
|
||||
/*
|
||||
* Pending list is not empty, we need to lock the index doesn't despite on
|
||||
* fastupdate state
|
||||
*/
|
||||
PredicateLockRelation(scan->indexRelation, scan->xs_snapshot);
|
||||
|
||||
pos.pendingBuffer = ReadBuffer(scan->indexRelation, blkno);
|
||||
LockBuffer(pos.pendingBuffer, GIN_SHARE);
|
||||
pos.firstOffset = FirstOffsetNumber;
|
||||
|
@ -22,6 +22,7 @@
|
||||
#include "storage/bufmgr.h"
|
||||
#include "storage/smgr.h"
|
||||
#include "storage/indexfsm.h"
|
||||
#include "storage/predicate.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "utils/rel.h"
|
||||
|
||||
@ -48,7 +49,7 @@ static IndexTuple
|
||||
addItemPointersToLeafTuple(GinState *ginstate,
|
||||
IndexTuple old,
|
||||
ItemPointerData *items, uint32 nitem,
|
||||
GinStatsData *buildStats)
|
||||
GinStatsData *buildStats, Buffer buffer)
|
||||
{
|
||||
OffsetNumber attnum;
|
||||
Datum key;
|
||||
@ -99,7 +100,8 @@ addItemPointersToLeafTuple(GinState *ginstate,
|
||||
postingRoot = createPostingTree(ginstate->index,
|
||||
oldItems,
|
||||
oldNPosting,
|
||||
buildStats);
|
||||
buildStats,
|
||||
buffer);
|
||||
|
||||
/* Now insert the TIDs-to-be-added into the posting tree */
|
||||
ginInsertItemPointers(ginstate->index, postingRoot,
|
||||
@ -127,7 +129,7 @@ static IndexTuple
|
||||
buildFreshLeafTuple(GinState *ginstate,
|
||||
OffsetNumber attnum, Datum key, GinNullCategory category,
|
||||
ItemPointerData *items, uint32 nitem,
|
||||
GinStatsData *buildStats)
|
||||
GinStatsData *buildStats, Buffer buffer)
|
||||
{
|
||||
IndexTuple res = NULL;
|
||||
GinPostingList *compressedList;
|
||||
@ -157,7 +159,7 @@ buildFreshLeafTuple(GinState *ginstate,
|
||||
* Initialize a new posting tree with the TIDs.
|
||||
*/
|
||||
postingRoot = createPostingTree(ginstate->index, items, nitem,
|
||||
buildStats);
|
||||
buildStats, buffer);
|
||||
|
||||
/* And save the root link in the result tuple */
|
||||
GinSetPostingTree(res, postingRoot);
|
||||
@ -217,17 +219,19 @@ ginEntryInsert(GinState *ginstate,
|
||||
return;
|
||||
}
|
||||
|
||||
GinCheckForSerializableConflictIn(btree.index, NULL, stack->buffer);
|
||||
/* modify an existing leaf entry */
|
||||
itup = addItemPointersToLeafTuple(ginstate, itup,
|
||||
items, nitem, buildStats);
|
||||
items, nitem, buildStats, stack->buffer);
|
||||
|
||||
insertdata.isDelete = true;
|
||||
}
|
||||
else
|
||||
{
|
||||
GinCheckForSerializableConflictIn(btree.index, NULL, stack->buffer);
|
||||
/* no match, so construct a new leaf entry */
|
||||
itup = buildFreshLeafTuple(ginstate, attnum, key, category,
|
||||
items, nitem, buildStats);
|
||||
items, nitem, buildStats, stack->buffer);
|
||||
}
|
||||
|
||||
/* Insert the new or modified leaf tuple */
|
||||
@ -513,6 +517,18 @@ gininsert(Relation index, Datum *values, bool *isnull,
|
||||
|
||||
memset(&collector, 0, sizeof(GinTupleCollector));
|
||||
|
||||
/*
|
||||
* With fastupdate on each scan and each insert begin with access to
|
||||
* pending list, so it effectively lock entire index. In this case
|
||||
* we aquire predicate lock and check for conflicts over index relation,
|
||||
* and hope that it will reduce locking overhead.
|
||||
*
|
||||
* Do not use GinCheckForSerializableConflictIn() here, because
|
||||
* it will do nothing (it does actual work only with fastupdate off).
|
||||
* Check for conflicts for entire index.
|
||||
*/
|
||||
CheckForSerializableConflictIn(index, NULL, InvalidBuffer);
|
||||
|
||||
for (i = 0; i < ginstate->origTupdesc->natts; i++)
|
||||
ginHeapTupleFastCollect(ginstate, &collector,
|
||||
(OffsetNumber) (i + 1),
|
||||
@ -523,6 +539,16 @@ gininsert(Relation index, Datum *values, bool *isnull,
|
||||
}
|
||||
else
|
||||
{
|
||||
GinStatsData stats;
|
||||
|
||||
/*
|
||||
* Fastupdate is off but if pending list isn't empty then we need to
|
||||
* check conflicts with PredicateLockRelation in scanPendingInsert().
|
||||
*/
|
||||
ginGetStats(index, &stats);
|
||||
if (stats.nPendingPages > 0)
|
||||
CheckForSerializableConflictIn(index, NULL, InvalidBuffer);
|
||||
|
||||
for (i = 0; i < ginstate->origTupdesc->natts; i++)
|
||||
ginHeapTupleInsert(ginstate, (OffsetNumber) (i + 1),
|
||||
values[i], isnull[i],
|
||||
|
@ -23,6 +23,7 @@
|
||||
#include "miscadmin.h"
|
||||
#include "storage/indexfsm.h"
|
||||
#include "storage/lmgr.h"
|
||||
#include "storage/predicate.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/index_selfuncs.h"
|
||||
#include "utils/typcache.h"
|
||||
@ -49,7 +50,7 @@ ginhandler(PG_FUNCTION_ARGS)
|
||||
amroutine->amsearchnulls = false;
|
||||
amroutine->amstorage = true;
|
||||
amroutine->amclusterable = false;
|
||||
amroutine->ampredlocks = false;
|
||||
amroutine->ampredlocks = true;
|
||||
amroutine->amcanparallel = false;
|
||||
amroutine->amkeytype = InvalidOid;
|
||||
|
||||
@ -716,3 +717,10 @@ ginUpdateStats(Relation index, const GinStatsData *stats)
|
||||
|
||||
END_CRIT_SECTION();
|
||||
}
|
||||
|
||||
void
|
||||
GinCheckForSerializableConflictIn(Relation relation, HeapTuple tuple, Buffer buffer)
|
||||
{
|
||||
if (!GinGetUseFastUpdate(relation))
|
||||
CheckForSerializableConflictIn(relation, tuple, buffer);
|
||||
}
|
||||
|
@ -22,6 +22,7 @@
|
||||
#include "postmaster/autovacuum.h"
|
||||
#include "storage/indexfsm.h"
|
||||
#include "storage/lmgr.h"
|
||||
#include "storage/predicate.h"
|
||||
#include "utils/memutils.h"
|
||||
|
||||
struct GinVacuumState
|
||||
@ -153,11 +154,18 @@ ginDeletePage(GinVacuumState *gvs, BlockNumber deleteBlkno, BlockNumber leftBlkn
|
||||
|
||||
LockBuffer(lBuffer, GIN_EXCLUSIVE);
|
||||
|
||||
page = BufferGetPage(dBuffer);
|
||||
rightlink = GinPageGetOpaque(page)->rightlink;
|
||||
|
||||
/*
|
||||
* Any insert which would have gone on the leaf block will now go to its
|
||||
* right sibling.
|
||||
*/
|
||||
PredicateLockPageCombine(gvs->index, deleteBlkno, rightlink);
|
||||
|
||||
START_CRIT_SECTION();
|
||||
|
||||
/* Unlink the page by changing left sibling's rightlink */
|
||||
page = BufferGetPage(dBuffer);
|
||||
rightlink = GinPageGetOpaque(page)->rightlink;
|
||||
|
||||
page = BufferGetPage(lBuffer);
|
||||
GinPageGetOpaque(page)->rightlink = rightlink;
|
||||
|
@ -380,6 +380,15 @@ then be trusted to ripple up to all levels and locations where
|
||||
conflicting predicate locks may exist. In case there is a page split,
|
||||
we need to copy predicate lock from an original page to all new pages.
|
||||
|
||||
* GIN searches acquire predicate locks only on the leaf pages
|
||||
of entry tree and posting tree. During a page split, a predicate locks are
|
||||
copied from the original page to the new page. In the same way predicate locks
|
||||
are copied from entry tree leaf page to freshly created posting tree root.
|
||||
However, when fast update is enabled, a predicate lock on the whole index
|
||||
relation is required. Fast update postpones the insertion of tuples into index
|
||||
structure by temporarily storing them into pending list. That makes us unable
|
||||
to detect r-w conflicts using page-level locks.
|
||||
|
||||
* The effects of page splits, overflows, consolidations, and
|
||||
removals must be carefully reviewed to ensure that predicate locks
|
||||
aren't "lost" during those operations, or kept with pages which could
|
||||
|
Reference in New Issue
Block a user