public inbox for [email protected]
help / color / mirror / Atom feed[PATCH v12 13/17] Separate TBM[Shared]Iterator and TBMIterateResult
19+ messages / 3 participants
[nested] [flat]
* [PATCH v12 13/17] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 30 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 47 ++++++++-------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/executor/nodeBitmapHeapscan.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
8 files changed, 113 insertions(+), 95 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb6..3aa457a29e1 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544e..033d5253394 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 46f1a374252..bd630e38fa8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2207,7 +2207,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2219,9 +2219,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
{
CHECK_FOR_INTERRUPTS();
- tbmres = bhs_iterate(scan->rs_bhs_iterator);
+ bhs_iterate(scan->rs_bhs_iterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2236,11 +2236,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2248,19 +2248,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* page are visible to our transaction.
*/
if (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2289,7 +2289,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2298,9 +2298,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2350,7 +2350,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- if (tbmres->ntuples < 0)
+ if (tbmres.ntuples < 0)
(*lossy_pages)++;
else
(*exact_pages)++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index fb79f57d7a6..d61965a2761 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -77,15 +77,16 @@ bhs_begin_iterate(TIDBitmap *tbm, dsa_pointer shared_area, dsa_area *personal_ar
return result;
}
-TBMIterateResult *
-bhs_iterate(BitmapHeapIterator *iterator)
+void
+bhs_iterate(BitmapHeapIterator *iterator, TBMIterateResult *result)
{
Assert(iterator);
+ Assert(result);
if (iterator->serial)
- return tbm_iterate(iterator->serial);
+ tbm_iterate(iterator->serial, result);
else
- return tbm_shared_iterate(iterator->parallel);
+ tbm_shared_iterate(iterator->parallel, result);
}
void
@@ -348,7 +349,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
BitmapHeapIterator *prefetch_iterator = node->pf_iterator;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -360,8 +361,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = bhs_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -394,8 +395,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = bhs_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -462,10 +463,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = bhs_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ bhs_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
bhs_end_iterate(prefetch_iterator);
@@ -473,7 +476,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -482,13 +485,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -501,7 +504,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -520,8 +523,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = bhs_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
bhs_end_iterate(prefetch_iterator);
@@ -529,17 +532,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index 1dc4c99bf99..309a44bdb84 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae1..3b432263bb0 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/executor/nodeBitmapHeapscan.h b/src/include/executor/nodeBitmapHeapscan.h
index cb56d20dc6f..3c330f86e62 100644
--- a/src/include/executor/nodeBitmapHeapscan.h
+++ b/src/include/executor/nodeBitmapHeapscan.h
@@ -34,7 +34,7 @@ typedef struct BitmapHeapIterator
struct TBMSharedIterator *parallel;
} BitmapHeapIterator;
-extern TBMIterateResult *bhs_iterate(BitmapHeapIterator *iterator);
+extern void bhs_iterate(BitmapHeapIterator *iterator, TBMIterateResult *result);
extern void bhs_end_iterate(BitmapHeapIterator *iterator);
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae52962..f000c1af28f 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--6jpz2j246qmht4bt
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v12-0014-Push-BitmapHeapScan-prefetch-code-into-heapam.c.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v10 13/17] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 30 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 47 ++++++++-------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/executor/nodeBitmapHeapscan.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
8 files changed, 113 insertions(+), 95 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb..3aa457a29e 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544..033d525339 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index d85fee1e50..105137396b 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2122,7 +2122,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2134,9 +2134,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
{
CHECK_FOR_INTERRUPTS();
- tbmres = bhs_iterate(scan->rs_bhs_iterator);
+ bhs_iterate(scan->rs_bhs_iterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2151,11 +2151,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2163,19 +2163,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* page are visible to our transaction.
*/
if (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2204,7 +2204,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2213,9 +2213,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2265,7 +2265,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- if (tbmres->ntuples < 0)
+ if (tbmres.ntuples < 0)
(*lossy_pages)++;
else
(*exact_pages)++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 076e1ff674..78f79aafff 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -77,15 +77,16 @@ bhs_begin_iterate(TIDBitmap *tbm, dsa_pointer shared_area, dsa_area *personal_ar
return result;
}
-TBMIterateResult *
-bhs_iterate(BitmapHeapIterator *iterator)
+void
+bhs_iterate(BitmapHeapIterator *iterator, TBMIterateResult *result)
{
Assert(iterator);
+ Assert(result);
if (iterator->serial)
- return tbm_iterate(iterator->serial);
+ tbm_iterate(iterator->serial, result);
else
- return tbm_shared_iterate(iterator->parallel);
+ tbm_shared_iterate(iterator->parallel, result);
}
void
@@ -348,7 +349,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
BitmapHeapIterator *prefetch_iterator = node->pf_iterator;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -360,8 +361,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = bhs_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -394,8 +395,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = bhs_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -462,10 +463,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = bhs_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ bhs_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
bhs_end_iterate(prefetch_iterator);
@@ -473,7 +476,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -482,13 +485,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -501,7 +504,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -520,8 +523,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = bhs_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
bhs_end_iterate(prefetch_iterator);
@@ -529,17 +532,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index 1dc4c99bf9..309a44bdb8 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae..3b432263bb 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/executor/nodeBitmapHeapscan.h b/src/include/executor/nodeBitmapHeapscan.h
index cb56d20dc6..3c330f86e6 100644
--- a/src/include/executor/nodeBitmapHeapscan.h
+++ b/src/include/executor/nodeBitmapHeapscan.h
@@ -34,7 +34,7 @@ typedef struct BitmapHeapIterator
struct TBMSharedIterator *parallel;
} BitmapHeapIterator;
-extern TBMIterateResult *bhs_iterate(BitmapHeapIterator *iterator);
+extern void bhs_iterate(BitmapHeapIterator *iterator, TBMIterateResult *result);
extern void bhs_end_iterate(BitmapHeapIterator *iterator);
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae5296..f000c1af28 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--3o7pc6dfau5a5hry
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v10-0014-Push-BitmapHeapScan-prefetch-code-into-heapam.c.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v11 13/17] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 30 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 47 ++++++++-------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/executor/nodeBitmapHeapscan.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
8 files changed, 113 insertions(+), 95 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb..3aa457a29e 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544..033d525339 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 81a7488007..f7e4d1094d 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2180,7 +2180,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2192,9 +2192,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
{
CHECK_FOR_INTERRUPTS();
- tbmres = bhs_iterate(scan->rs_bhs_iterator);
+ bhs_iterate(scan->rs_bhs_iterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2209,11 +2209,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2221,19 +2221,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* page are visible to our transaction.
*/
if (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2262,7 +2262,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2271,9 +2271,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2323,7 +2323,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- if (tbmres->ntuples < 0)
+ if (tbmres.ntuples < 0)
(*lossy_pages)++;
else
(*exact_pages)++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 076e1ff674..78f79aafff 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -77,15 +77,16 @@ bhs_begin_iterate(TIDBitmap *tbm, dsa_pointer shared_area, dsa_area *personal_ar
return result;
}
-TBMIterateResult *
-bhs_iterate(BitmapHeapIterator *iterator)
+void
+bhs_iterate(BitmapHeapIterator *iterator, TBMIterateResult *result)
{
Assert(iterator);
+ Assert(result);
if (iterator->serial)
- return tbm_iterate(iterator->serial);
+ tbm_iterate(iterator->serial, result);
else
- return tbm_shared_iterate(iterator->parallel);
+ tbm_shared_iterate(iterator->parallel, result);
}
void
@@ -348,7 +349,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
BitmapHeapIterator *prefetch_iterator = node->pf_iterator;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -360,8 +361,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = bhs_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -394,8 +395,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = bhs_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -462,10 +463,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = bhs_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ bhs_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
bhs_end_iterate(prefetch_iterator);
@@ -473,7 +476,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -482,13 +485,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -501,7 +504,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -520,8 +523,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = bhs_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
bhs_end_iterate(prefetch_iterator);
@@ -529,17 +532,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index 1dc4c99bf9..309a44bdb8 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae..3b432263bb 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/executor/nodeBitmapHeapscan.h b/src/include/executor/nodeBitmapHeapscan.h
index cb56d20dc6..3c330f86e6 100644
--- a/src/include/executor/nodeBitmapHeapscan.h
+++ b/src/include/executor/nodeBitmapHeapscan.h
@@ -34,7 +34,7 @@ typedef struct BitmapHeapIterator
struct TBMSharedIterator *parallel;
} BitmapHeapIterator;
-extern TBMIterateResult *bhs_iterate(BitmapHeapIterator *iterator);
+extern void bhs_iterate(BitmapHeapIterator *iterator, TBMIterateResult *result);
extern void bhs_end_iterate(BitmapHeapIterator *iterator);
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae5296..f000c1af28 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--owzzsiozz6hgpp7e
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v11-0014-Push-BitmapHeapScan-prefetch-code-into-heapam.c.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v6 12/14] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 32 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 38 ++++++------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
7 files changed, 108 insertions(+), 91 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb6..3aa457a29e1 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544e..033d5253394 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index e038e60cd8f..022753e203a 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2119,7 +2119,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2132,11 +2132,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
CHECK_FOR_INTERRUPTS();
if (scan->shared_tbmiterator)
- tbmres = tbm_shared_iterate(scan->shared_tbmiterator);
+ tbm_shared_iterate(scan->shared_tbmiterator, &tbmres);
else
- tbmres = tbm_iterate(scan->tbmiterator);
+ tbm_iterate(scan->tbmiterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2151,11 +2151,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2163,19 +2163,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* the page are visible to our transaction.
*/
if (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2204,7 +2204,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2213,9 +2213,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2265,7 +2265,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- *lossy = tbmres->ntuples < 0;
+ *lossy = tbmres.ntuples < 0;
/*
* Return true to indicate that a valid block was found and the bitmap is
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 0924613b247..b3b9448627b 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -320,7 +320,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
{
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -334,8 +334,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = tbm_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -370,8 +370,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -439,10 +439,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ tbm_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_iterate(prefetch_iterator);
@@ -450,7 +452,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -459,13 +461,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -480,7 +482,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -499,8 +501,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_shared_iterate(prefetch_iterator);
@@ -508,17 +510,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index d2bf8f44d50..7d038c2018d 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae1..3b432263bb0 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae52962..f000c1af28f 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--w4wcjcocxsm37usi
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v6-0013-v7-Streaming-Read-API.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v7 11/13] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 32 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 38 ++++++------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
7 files changed, 108 insertions(+), 91 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb6..3aa457a29e1 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544e..033d5253394 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index e038e60cd8f..022753e203a 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2119,7 +2119,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2132,11 +2132,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
CHECK_FOR_INTERRUPTS();
if (scan->shared_tbmiterator)
- tbmres = tbm_shared_iterate(scan->shared_tbmiterator);
+ tbm_shared_iterate(scan->shared_tbmiterator, &tbmres);
else
- tbmres = tbm_iterate(scan->tbmiterator);
+ tbm_iterate(scan->tbmiterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2151,11 +2151,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2163,19 +2163,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* the page are visible to our transaction.
*/
if (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2204,7 +2204,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2213,9 +2213,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2265,7 +2265,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- *lossy = tbmres->ntuples < 0;
+ *lossy = tbmres.ntuples < 0;
/*
* Return true to indicate that a valid block was found and the bitmap is
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index b1dfa582c7d..43df0ac9964 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -321,7 +321,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
{
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -335,8 +335,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = tbm_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -371,8 +371,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -440,10 +440,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ tbm_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_iterate(prefetch_iterator);
@@ -451,7 +453,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -460,13 +462,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -481,7 +483,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -500,8 +502,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_shared_iterate(prefetch_iterator);
@@ -509,17 +511,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index d2bf8f44d50..7d038c2018d 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae1..3b432263bb0 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae52962..f000c1af28f 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--kqqpqghcwbcc3dt5
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v7-0012-v7-Streaming-Read-API.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v8 12/17] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 32 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 38 ++++++------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
7 files changed, 108 insertions(+), 91 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb..3aa457a29e 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544..033d525339 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 266b34fe6b..adfc77684a 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2122,7 +2122,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2135,11 +2135,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
CHECK_FOR_INTERRUPTS();
if (scan->shared_tbmiterator)
- tbmres = tbm_shared_iterate(scan->shared_tbmiterator);
+ tbm_shared_iterate(scan->shared_tbmiterator, &tbmres);
else
- tbmres = tbm_iterate(scan->tbmiterator);
+ tbm_iterate(scan->tbmiterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2154,11 +2154,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2166,19 +2166,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* page are visible to our transaction.
*/
if (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2207,7 +2207,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2216,9 +2216,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2268,7 +2268,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- if (tbmres->ntuples < 0)
+ if (tbmres.ntuples < 0)
(*lossy_pages)++;
else
(*exact_pages)++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 96b55507a3..51c4360205 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -316,7 +316,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
{
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -330,8 +330,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = tbm_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -366,8 +366,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -435,10 +435,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ tbm_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_iterate(prefetch_iterator);
@@ -446,7 +448,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -455,13 +457,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -476,7 +478,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -495,8 +497,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_shared_iterate(prefetch_iterator);
@@ -504,17 +506,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index 1dc4c99bf9..309a44bdb8 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae..3b432263bb 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae5296..f000c1af28 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--xqq4defy3uncu6k6
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v8-0013-Push-BitmapHeapScan-prefetch-code-into-heapam.c.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v9 12/17] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 32 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 38 ++++++------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
7 files changed, 108 insertions(+), 91 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb..3aa457a29e 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544..033d525339 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 266b34fe6b..adfc77684a 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2122,7 +2122,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2135,11 +2135,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
CHECK_FOR_INTERRUPTS();
if (scan->shared_tbmiterator)
- tbmres = tbm_shared_iterate(scan->shared_tbmiterator);
+ tbm_shared_iterate(scan->shared_tbmiterator, &tbmres);
else
- tbmres = tbm_iterate(scan->tbmiterator);
+ tbm_iterate(scan->tbmiterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2154,11 +2154,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2166,19 +2166,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* page are visible to our transaction.
*/
if (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2207,7 +2207,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2216,9 +2216,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2268,7 +2268,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- if (tbmres->ntuples < 0)
+ if (tbmres.ntuples < 0)
(*lossy_pages)++;
else
(*exact_pages)++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 96b55507a3..51c4360205 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -316,7 +316,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
{
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -330,8 +330,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = tbm_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -366,8 +366,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -435,10 +435,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ tbm_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_iterate(prefetch_iterator);
@@ -446,7 +448,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -455,13 +457,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -476,7 +478,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -495,8 +497,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_shared_iterate(prefetch_iterator);
@@ -504,17 +506,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index 1dc4c99bf9..309a44bdb8 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae..3b432263bb 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae5296..f000c1af28 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--7mdtsjmrzitrgzgx
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v9-0013-Push-BitmapHeapScan-prefetch-code-into-heapam.c.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v10 13/17] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 30 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 47 ++++++++-------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/executor/nodeBitmapHeapscan.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
8 files changed, 113 insertions(+), 95 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb..3aa457a29e 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544..033d525339 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index d85fee1e50..105137396b 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2122,7 +2122,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2134,9 +2134,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
{
CHECK_FOR_INTERRUPTS();
- tbmres = bhs_iterate(scan->rs_bhs_iterator);
+ bhs_iterate(scan->rs_bhs_iterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2151,11 +2151,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2163,19 +2163,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* page are visible to our transaction.
*/
if (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2204,7 +2204,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2213,9 +2213,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2265,7 +2265,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- if (tbmres->ntuples < 0)
+ if (tbmres.ntuples < 0)
(*lossy_pages)++;
else
(*exact_pages)++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 076e1ff674..78f79aafff 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -77,15 +77,16 @@ bhs_begin_iterate(TIDBitmap *tbm, dsa_pointer shared_area, dsa_area *personal_ar
return result;
}
-TBMIterateResult *
-bhs_iterate(BitmapHeapIterator *iterator)
+void
+bhs_iterate(BitmapHeapIterator *iterator, TBMIterateResult *result)
{
Assert(iterator);
+ Assert(result);
if (iterator->serial)
- return tbm_iterate(iterator->serial);
+ tbm_iterate(iterator->serial, result);
else
- return tbm_shared_iterate(iterator->parallel);
+ tbm_shared_iterate(iterator->parallel, result);
}
void
@@ -348,7 +349,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
BitmapHeapIterator *prefetch_iterator = node->pf_iterator;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -360,8 +361,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = bhs_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -394,8 +395,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = bhs_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -462,10 +463,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = bhs_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ bhs_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
bhs_end_iterate(prefetch_iterator);
@@ -473,7 +476,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -482,13 +485,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -501,7 +504,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -520,8 +523,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = bhs_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
bhs_end_iterate(prefetch_iterator);
@@ -529,17 +532,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index 1dc4c99bf9..309a44bdb8 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae..3b432263bb 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/executor/nodeBitmapHeapscan.h b/src/include/executor/nodeBitmapHeapscan.h
index cb56d20dc6..3c330f86e6 100644
--- a/src/include/executor/nodeBitmapHeapscan.h
+++ b/src/include/executor/nodeBitmapHeapscan.h
@@ -34,7 +34,7 @@ typedef struct BitmapHeapIterator
struct TBMSharedIterator *parallel;
} BitmapHeapIterator;
-extern TBMIterateResult *bhs_iterate(BitmapHeapIterator *iterator);
+extern void bhs_iterate(BitmapHeapIterator *iterator, TBMIterateResult *result);
extern void bhs_end_iterate(BitmapHeapIterator *iterator);
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae5296..f000c1af28 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--3o7pc6dfau5a5hry
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v10-0014-Push-BitmapHeapScan-prefetch-code-into-heapam.c.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v11 13/17] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 30 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 47 ++++++++-------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/executor/nodeBitmapHeapscan.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
8 files changed, 113 insertions(+), 95 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb..3aa457a29e 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544..033d525339 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 81a7488007..f7e4d1094d 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2180,7 +2180,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2192,9 +2192,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
{
CHECK_FOR_INTERRUPTS();
- tbmres = bhs_iterate(scan->rs_bhs_iterator);
+ bhs_iterate(scan->rs_bhs_iterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2209,11 +2209,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2221,19 +2221,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* page are visible to our transaction.
*/
if (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2262,7 +2262,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2271,9 +2271,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2323,7 +2323,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- if (tbmres->ntuples < 0)
+ if (tbmres.ntuples < 0)
(*lossy_pages)++;
else
(*exact_pages)++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 076e1ff674..78f79aafff 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -77,15 +77,16 @@ bhs_begin_iterate(TIDBitmap *tbm, dsa_pointer shared_area, dsa_area *personal_ar
return result;
}
-TBMIterateResult *
-bhs_iterate(BitmapHeapIterator *iterator)
+void
+bhs_iterate(BitmapHeapIterator *iterator, TBMIterateResult *result)
{
Assert(iterator);
+ Assert(result);
if (iterator->serial)
- return tbm_iterate(iterator->serial);
+ tbm_iterate(iterator->serial, result);
else
- return tbm_shared_iterate(iterator->parallel);
+ tbm_shared_iterate(iterator->parallel, result);
}
void
@@ -348,7 +349,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
BitmapHeapIterator *prefetch_iterator = node->pf_iterator;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -360,8 +361,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = bhs_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -394,8 +395,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = bhs_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -462,10 +463,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = bhs_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ bhs_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
bhs_end_iterate(prefetch_iterator);
@@ -473,7 +476,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -482,13 +485,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -501,7 +504,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -520,8 +523,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = bhs_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ bhs_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
bhs_end_iterate(prefetch_iterator);
@@ -529,17 +532,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index 1dc4c99bf9..309a44bdb8 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae..3b432263bb 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/executor/nodeBitmapHeapscan.h b/src/include/executor/nodeBitmapHeapscan.h
index cb56d20dc6..3c330f86e6 100644
--- a/src/include/executor/nodeBitmapHeapscan.h
+++ b/src/include/executor/nodeBitmapHeapscan.h
@@ -34,7 +34,7 @@ typedef struct BitmapHeapIterator
struct TBMSharedIterator *parallel;
} BitmapHeapIterator;
-extern TBMIterateResult *bhs_iterate(BitmapHeapIterator *iterator);
+extern void bhs_iterate(BitmapHeapIterator *iterator, TBMIterateResult *result);
extern void bhs_end_iterate(BitmapHeapIterator *iterator);
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae5296..f000c1af28 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--owzzsiozz6hgpp7e
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v11-0014-Push-BitmapHeapScan-prefetch-code-into-heapam.c.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v6 12/14] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 32 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 38 ++++++------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
7 files changed, 108 insertions(+), 91 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb6..3aa457a29e1 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544e..033d5253394 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index e038e60cd8f..022753e203a 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2119,7 +2119,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2132,11 +2132,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
CHECK_FOR_INTERRUPTS();
if (scan->shared_tbmiterator)
- tbmres = tbm_shared_iterate(scan->shared_tbmiterator);
+ tbm_shared_iterate(scan->shared_tbmiterator, &tbmres);
else
- tbmres = tbm_iterate(scan->tbmiterator);
+ tbm_iterate(scan->tbmiterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2151,11 +2151,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2163,19 +2163,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* the page are visible to our transaction.
*/
if (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2204,7 +2204,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2213,9 +2213,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2265,7 +2265,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- *lossy = tbmres->ntuples < 0;
+ *lossy = tbmres.ntuples < 0;
/*
* Return true to indicate that a valid block was found and the bitmap is
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 0924613b247..b3b9448627b 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -320,7 +320,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
{
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -334,8 +334,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = tbm_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -370,8 +370,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -439,10 +439,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ tbm_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_iterate(prefetch_iterator);
@@ -450,7 +452,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -459,13 +461,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -480,7 +482,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -499,8 +501,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_shared_iterate(prefetch_iterator);
@@ -508,17 +510,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index d2bf8f44d50..7d038c2018d 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae1..3b432263bb0 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae52962..f000c1af28f 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--w4wcjcocxsm37usi
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v6-0013-v7-Streaming-Read-API.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v7 11/13] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 32 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 38 ++++++------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
7 files changed, 108 insertions(+), 91 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb6..3aa457a29e1 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544e..033d5253394 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index e038e60cd8f..022753e203a 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2119,7 +2119,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2132,11 +2132,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
CHECK_FOR_INTERRUPTS();
if (scan->shared_tbmiterator)
- tbmres = tbm_shared_iterate(scan->shared_tbmiterator);
+ tbm_shared_iterate(scan->shared_tbmiterator, &tbmres);
else
- tbmres = tbm_iterate(scan->tbmiterator);
+ tbm_iterate(scan->tbmiterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2151,11 +2151,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2163,19 +2163,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* the page are visible to our transaction.
*/
if (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2204,7 +2204,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2213,9 +2213,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2265,7 +2265,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- *lossy = tbmres->ntuples < 0;
+ *lossy = tbmres.ntuples < 0;
/*
* Return true to indicate that a valid block was found and the bitmap is
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index b1dfa582c7d..43df0ac9964 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -321,7 +321,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
{
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -335,8 +335,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = tbm_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -371,8 +371,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -440,10 +440,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ tbm_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_iterate(prefetch_iterator);
@@ -451,7 +453,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -460,13 +462,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -481,7 +483,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -500,8 +502,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_shared_iterate(prefetch_iterator);
@@ -509,17 +511,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index d2bf8f44d50..7d038c2018d 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae1..3b432263bb0 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae52962..f000c1af28f 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--kqqpqghcwbcc3dt5
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v7-0012-v7-Streaming-Read-API.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v8 12/17] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 32 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 38 ++++++------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
7 files changed, 108 insertions(+), 91 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb..3aa457a29e 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544..033d525339 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 266b34fe6b..adfc77684a 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2122,7 +2122,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2135,11 +2135,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
CHECK_FOR_INTERRUPTS();
if (scan->shared_tbmiterator)
- tbmres = tbm_shared_iterate(scan->shared_tbmiterator);
+ tbm_shared_iterate(scan->shared_tbmiterator, &tbmres);
else
- tbmres = tbm_iterate(scan->tbmiterator);
+ tbm_iterate(scan->tbmiterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2154,11 +2154,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2166,19 +2166,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* page are visible to our transaction.
*/
if (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2207,7 +2207,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2216,9 +2216,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2268,7 +2268,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- if (tbmres->ntuples < 0)
+ if (tbmres.ntuples < 0)
(*lossy_pages)++;
else
(*exact_pages)++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 96b55507a3..51c4360205 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -316,7 +316,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
{
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -330,8 +330,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = tbm_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -366,8 +366,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -435,10 +435,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ tbm_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_iterate(prefetch_iterator);
@@ -446,7 +448,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -455,13 +457,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -476,7 +478,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -495,8 +497,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_shared_iterate(prefetch_iterator);
@@ -504,17 +506,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index 1dc4c99bf9..309a44bdb8 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae..3b432263bb 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae5296..f000c1af28 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--xqq4defy3uncu6k6
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v8-0013-Push-BitmapHeapScan-prefetch-code-into-heapam.c.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v9 12/17] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 32 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 38 ++++++------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
7 files changed, 108 insertions(+), 91 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb..3aa457a29e 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544..033d525339 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 266b34fe6b..adfc77684a 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2122,7 +2122,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2135,11 +2135,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
CHECK_FOR_INTERRUPTS();
if (scan->shared_tbmiterator)
- tbmres = tbm_shared_iterate(scan->shared_tbmiterator);
+ tbm_shared_iterate(scan->shared_tbmiterator, &tbmres);
else
- tbmres = tbm_iterate(scan->tbmiterator);
+ tbm_iterate(scan->tbmiterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2154,11 +2154,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2166,19 +2166,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* page are visible to our transaction.
*/
if (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2207,7 +2207,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2216,9 +2216,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2268,7 +2268,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- if (tbmres->ntuples < 0)
+ if (tbmres.ntuples < 0)
(*lossy_pages)++;
else
(*exact_pages)++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 96b55507a3..51c4360205 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -316,7 +316,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
{
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -330,8 +330,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = tbm_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -366,8 +366,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -435,10 +435,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ tbm_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_iterate(prefetch_iterator);
@@ -446,7 +448,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -455,13 +457,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -476,7 +478,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -495,8 +497,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_shared_iterate(prefetch_iterator);
@@ -504,17 +506,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index 1dc4c99bf9..309a44bdb8 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae..3b432263bb 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae5296..f000c1af28 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--7mdtsjmrzitrgzgx
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v9-0013-Push-BitmapHeapScan-prefetch-code-into-heapam.c.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v6 12/14] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 32 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 38 ++++++------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
7 files changed, 108 insertions(+), 91 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb6..3aa457a29e1 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544e..033d5253394 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index e038e60cd8f..022753e203a 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2119,7 +2119,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2132,11 +2132,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
CHECK_FOR_INTERRUPTS();
if (scan->shared_tbmiterator)
- tbmres = tbm_shared_iterate(scan->shared_tbmiterator);
+ tbm_shared_iterate(scan->shared_tbmiterator, &tbmres);
else
- tbmres = tbm_iterate(scan->tbmiterator);
+ tbm_iterate(scan->tbmiterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2151,11 +2151,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2163,19 +2163,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* the page are visible to our transaction.
*/
if (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2204,7 +2204,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2213,9 +2213,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2265,7 +2265,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- *lossy = tbmres->ntuples < 0;
+ *lossy = tbmres.ntuples < 0;
/*
* Return true to indicate that a valid block was found and the bitmap is
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 0924613b247..b3b9448627b 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -320,7 +320,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
{
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -334,8 +334,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = tbm_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -370,8 +370,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -439,10 +439,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ tbm_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_iterate(prefetch_iterator);
@@ -450,7 +452,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -459,13 +461,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -480,7 +482,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -499,8 +501,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_shared_iterate(prefetch_iterator);
@@ -508,17 +510,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index d2bf8f44d50..7d038c2018d 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae1..3b432263bb0 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae52962..f000c1af28f 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--w4wcjcocxsm37usi
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v6-0013-v7-Streaming-Read-API.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v7 11/13] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 32 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 38 ++++++------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
7 files changed, 108 insertions(+), 91 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb6..3aa457a29e1 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544e..033d5253394 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index e038e60cd8f..022753e203a 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2119,7 +2119,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2132,11 +2132,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
CHECK_FOR_INTERRUPTS();
if (scan->shared_tbmiterator)
- tbmres = tbm_shared_iterate(scan->shared_tbmiterator);
+ tbm_shared_iterate(scan->shared_tbmiterator, &tbmres);
else
- tbmres = tbm_iterate(scan->tbmiterator);
+ tbm_iterate(scan->tbmiterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2151,11 +2151,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2163,19 +2163,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* the page are visible to our transaction.
*/
if (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2204,7 +2204,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2213,9 +2213,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2265,7 +2265,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- *lossy = tbmres->ntuples < 0;
+ *lossy = tbmres.ntuples < 0;
/*
* Return true to indicate that a valid block was found and the bitmap is
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index b1dfa582c7d..43df0ac9964 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -321,7 +321,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
{
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -335,8 +335,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = tbm_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -371,8 +371,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -440,10 +440,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ tbm_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_iterate(prefetch_iterator);
@@ -451,7 +453,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -460,13 +462,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -481,7 +483,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -500,8 +502,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_shared_iterate(prefetch_iterator);
@@ -509,17 +511,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index d2bf8f44d50..7d038c2018d 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae1..3b432263bb0 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae52962..f000c1af28f 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--kqqpqghcwbcc3dt5
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v7-0012-v7-Streaming-Read-API.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v8 12/17] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 32 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 38 ++++++------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
7 files changed, 108 insertions(+), 91 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb..3aa457a29e 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544..033d525339 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 266b34fe6b..adfc77684a 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2122,7 +2122,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2135,11 +2135,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
CHECK_FOR_INTERRUPTS();
if (scan->shared_tbmiterator)
- tbmres = tbm_shared_iterate(scan->shared_tbmiterator);
+ tbm_shared_iterate(scan->shared_tbmiterator, &tbmres);
else
- tbmres = tbm_iterate(scan->tbmiterator);
+ tbm_iterate(scan->tbmiterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2154,11 +2154,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2166,19 +2166,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* page are visible to our transaction.
*/
if (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2207,7 +2207,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2216,9 +2216,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2268,7 +2268,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- if (tbmres->ntuples < 0)
+ if (tbmres.ntuples < 0)
(*lossy_pages)++;
else
(*exact_pages)++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 96b55507a3..51c4360205 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -316,7 +316,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
{
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -330,8 +330,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = tbm_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -366,8 +366,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -435,10 +435,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ tbm_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_iterate(prefetch_iterator);
@@ -446,7 +448,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -455,13 +457,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -476,7 +478,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -495,8 +497,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_shared_iterate(prefetch_iterator);
@@ -504,17 +506,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index 1dc4c99bf9..309a44bdb8 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae..3b432263bb 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae5296..f000c1af28 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--xqq4defy3uncu6k6
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v8-0013-Push-BitmapHeapScan-prefetch-code-into-heapam.c.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* [PATCH v9 12/17] Separate TBM[Shared]Iterator and TBMIterateResult
@ 2024-02-16 02:23 Melanie Plageman <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Melanie Plageman @ 2024-02-16 02:23 UTC (permalink / raw)
Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.
This will allow multiple TBMIterateResults to exist concurrently
allowing asynchronous use of the TIDBitmap for prefetching, for example.
tbm_[shared]_iterate() now sets blockno to InvalidBlockNumber when the
bitmap is exhausted instead of returning NULL.
BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.
Because GIN only needs a single TBMIterateResult, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
src/backend/access/gin/ginget.c | 48 +++++++++------
src/backend/access/gin/ginscan.c | 2 +-
src/backend/access/heap/heapam_handler.c | 32 +++++-----
src/backend/executor/nodeBitmapHeapscan.c | 38 ++++++------
src/backend/nodes/tidbitmap.c | 73 ++++++++++++-----------
src/include/access/gin_private.h | 2 +-
src/include/nodes/tidbitmap.h | 4 +-
7 files changed, 108 insertions(+), 91 deletions(-)
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb..3aa457a29e 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
entry->list = NULL;
entry->nlist = 0;
entry->matchBitmap = NULL;
- entry->matchResult = NULL;
entry->reduceResult = false;
entry->predictNumberResult = 0;
+ /*
+ * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+ * places were we previously set matchResult to NULL, I just set blockno
+ * to InvalidBlockNumber. It seems like this should be okay because that
+ * is usually what we check before using the matchResult members. But it
+ * might be safer to zero out the offsets array. But that is expensive.
+ */
+ entry->matchResult.blockno = InvalidBlockNumber;
+ entry->matchResult.ntuples = 0;
+ entry->matchResult.recheck = true;
+ memset(entry->matchResult.offsets, 0,
+ sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
/*
* we should find entry, and begin scan of posting tree or just store
* posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
{
if (entry->matchIterator)
tbm_end_iterate(entry->matchIterator);
+ entry->matchResult.blockno = InvalidBlockNumber;
entry->matchIterator = NULL;
tbm_free(entry->matchBitmap);
entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
{
/*
* If we've exhausted all items on this block, move to next block
- * in the bitmap.
+ * in the bitmap. tbm_iterate() sets matchResult->blockno to
+ * InvalidBlockNumber when the bitmap is exhausted.
*/
- while (entry->matchResult == NULL ||
- (entry->matchResult->ntuples >= 0 &&
- entry->offset >= entry->matchResult->ntuples) ||
- entry->matchResult->blockno < advancePastBlk ||
+ while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+ (entry->matchResult.ntuples >= 0 &&
+ entry->offset >= entry->matchResult.ntuples) ||
+ entry->matchResult.blockno < advancePastBlk ||
(ItemPointerIsLossyPage(&advancePast) &&
- entry->matchResult->blockno == advancePastBlk))
+ entry->matchResult.blockno == advancePastBlk))
{
- entry->matchResult = tbm_iterate(entry->matchIterator);
+ tbm_iterate(entry->matchIterator, &entry->matchResult);
- if (entry->matchResult == NULL)
+ if (!BlockNumberIsValid(entry->matchResult.blockno))
{
ItemPointerSetInvalid(&entry->curItem);
tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* We're now on the first page after advancePast which has any
* items on it. If it's a lossy result, return that.
*/
- if (entry->matchResult->ntuples < 0)
+ if (entry->matchResult.ntuples < 0)
{
ItemPointerSetLossyPage(&entry->curItem,
- entry->matchResult->blockno);
+ entry->matchResult.blockno);
/*
* We might as well fall out of the loop; we could not
@@ -875,27 +889,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
* Not a lossy page. Skip over any offsets <= advancePast, and
* return that.
*/
- if (entry->matchResult->blockno == advancePastBlk)
+ if (entry->matchResult.blockno == advancePastBlk)
{
/*
* First, do a quick check against the last offset on the
* page. If that's > advancePast, so are all the other
* offsets, so just go back to the top to get the next page.
*/
- if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+ if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
{
- entry->offset = entry->matchResult->ntuples;
+ entry->offset = entry->matchResult.ntuples;
continue;
}
/* Otherwise scan to find the first item > advancePast */
- while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+ while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
entry->offset++;
}
ItemPointerSet(&entry->curItem,
- entry->matchResult->blockno,
- entry->matchResult->offsets[entry->offset]);
+ entry->matchResult.blockno,
+ entry->matchResult.offsets[entry->offset]);
entry->offset++;
/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index af24d38544..033d525339 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
ItemPointerSetMin(&scanEntry->curItem);
scanEntry->matchBitmap = NULL;
scanEntry->matchIterator = NULL;
- scanEntry->matchResult = NULL;
+ scanEntry->matchResult.blockno = InvalidBlockNumber;
scanEntry->list = NULL;
scanEntry->nlist = 0;
scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 266b34fe6b..adfc77684a 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2122,7 +2122,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Buffer buffer;
Snapshot snapshot;
int ntup;
- TBMIterateResult *tbmres;
+ TBMIterateResult tbmres;
hscan->rs_cindex = 0;
hscan->rs_ntuples = 0;
@@ -2135,11 +2135,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
CHECK_FOR_INTERRUPTS();
if (scan->shared_tbmiterator)
- tbmres = tbm_shared_iterate(scan->shared_tbmiterator);
+ tbm_shared_iterate(scan->shared_tbmiterator, &tbmres);
else
- tbmres = tbm_iterate(scan->tbmiterator);
+ tbm_iterate(scan->tbmiterator, &tbmres);
- if (tbmres == NULL)
+ if (!BlockNumberIsValid(tbmres.blockno))
{
/* no more entries in the bitmap */
Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2154,11 +2154,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* isolation though, as we need to examine all invisible tuples
* reachable by the index.
*/
- } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+ } while (!IsolationIsSerializable() && tbmres.blockno >= hscan->rs_nblocks);
/* Got a valid block */
- *blockno = tbmres->blockno;
- *recheck = tbmres->recheck;
+ *blockno = tbmres.blockno;
+ *recheck = tbmres.recheck;
/*
* We can skip fetching the heap page if we don't need any fields from the
@@ -2166,19 +2166,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
* page are visible to our transaction.
*/
if (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmres->recheck &&
- VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+ !tbmres.recheck &&
+ VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
{
/* can't be lossy in the skip_fetch case */
- Assert(tbmres->ntuples >= 0);
+ Assert(tbmres.ntuples >= 0);
Assert(hscan->rs_empty_tuples_pending >= 0);
- hscan->rs_empty_tuples_pending += tbmres->ntuples;
+ hscan->rs_empty_tuples_pending += tbmres.ntuples;
return true;
}
- block = tbmres->blockno;
+ block = tbmres.blockno;
/*
* Acquire pin on the target heap page, trading in any pin we held before.
@@ -2207,7 +2207,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
/*
* We need two separate strategies for lossy and non-lossy cases.
*/
- if (tbmres->ntuples >= 0)
+ if (tbmres.ntuples >= 0)
{
/*
* Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2216,9 +2216,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
*/
int curslot;
- for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+ for (curslot = 0; curslot < tbmres.ntuples; curslot++)
{
- OffsetNumber offnum = tbmres->offsets[curslot];
+ OffsetNumber offnum = tbmres.offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
@@ -2268,7 +2268,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
Assert(ntup <= MaxHeapTuplesPerPage);
hscan->rs_ntuples = ntup;
- if (tbmres->ntuples < 0)
+ if (tbmres.ntuples < 0)
(*lossy_pages)++;
else
(*exact_pages)++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 96b55507a3..51c4360205 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -316,7 +316,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
{
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
if (pstate == NULL)
{
@@ -330,8 +330,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
else if (prefetch_iterator)
{
/* Do not let the prefetch iterator get behind the main one */
- tbmpre = tbm_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
return;
}
@@ -366,8 +366,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
*/
if (prefetch_iterator)
{
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- node->pfblockno = tbmpre ? tbmpre->blockno : InvalidBlockNumber;
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ node->pfblockno = tbmpre.blockno;
}
}
}
@@ -435,10 +435,12 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (node->prefetch_pages < node->prefetch_target)
{
- TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+ TBMIterateResult tbmpre;
bool skip_fetch;
- if (tbmpre == NULL)
+ tbm_iterate(prefetch_iterator, &tbmpre);
+
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_iterate(prefetch_iterator);
@@ -446,7 +448,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
node->prefetch_pages++;
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/*
* If we expect not to have to actually read this heap page,
@@ -455,13 +457,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
* prefetch_pages?)
*/
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
@@ -476,7 +478,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
{
while (1)
{
- TBMIterateResult *tbmpre;
+ TBMIterateResult tbmpre;
bool do_prefetch = false;
bool skip_fetch;
@@ -495,8 +497,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
if (!do_prefetch)
return;
- tbmpre = tbm_shared_iterate(prefetch_iterator);
- if (tbmpre == NULL)
+ tbm_shared_iterate(prefetch_iterator, &tbmpre);
+ if (!BlockNumberIsValid(tbmpre.blockno))
{
/* No more pages to prefetch */
tbm_end_shared_iterate(prefetch_iterator);
@@ -504,17 +506,17 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
break;
}
- node->pfblockno = tbmpre->blockno;
+ node->pfblockno = tbmpre.blockno;
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLE) &&
- !tbmpre->recheck &&
+ !tbmpre.recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
- tbmpre->blockno,
+ tbmpre.blockno,
&node->pvmbuffer));
if (!skip_fetch)
- PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+ PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
}
}
}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index 1dc4c99bf9..309a44bdb8 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMIterator
int spageptr; /* next spages index */
int schunkptr; /* next schunks index */
int schunkbit; /* next bit to check in current schunk */
- TBMIterateResult output;
};
/*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
PTEntryArray *ptbase; /* pagetable element array */
PTIterationArray *ptpages; /* sorted exact page index list */
PTIterationArray *ptchunks; /* sorted lossy page index list */
- TBMIterateResult output;
};
/* Local function prototypes */
@@ -944,20 +942,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
/*
* tbm_iterate - scan through next page of a TIDBitmap
*
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan. Pages are guaranteed to be delivered in numerical
- * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition. If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway. (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition. If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway. (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
*/
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
{
TIDBitmap *tbm = iterator->tbm;
- TBMIterateResult *output = &(iterator->output);
Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
@@ -985,6 +984,7 @@ tbm_iterate(TBMIterator *iterator)
* If both chunk and per-page data remain, must output the numerically
* earlier page.
*/
+ Assert(tbmres);
if (iterator->schunkptr < tbm->nchunks)
{
PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -995,11 +995,11 @@ tbm_iterate(TBMIterator *iterator)
chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
iterator->schunkbit++;
- return output;
+ return;
}
}
@@ -1015,16 +1015,17 @@ tbm_iterate(TBMIterator *iterator)
page = tbm->spages[iterator->spageptr];
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
iterator->spageptr++;
- return output;
+ return;
}
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
@@ -1034,10 +1035,9 @@ tbm_iterate(TBMIterator *iterator)
* across multiple processes. We need to acquire the iterator LWLock,
* before accessing the shared members.
*/
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
{
- TBMIterateResult *output = &iterator->output;
TBMSharedIteratorState *istate = iterator->state;
PagetableEntry *ptbase = NULL;
int *idxpages = NULL;
@@ -1088,13 +1088,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
{
/* Return a lossy page indicator from the chunk */
- output->blockno = chunk_blockno;
- output->ntuples = -1;
- output->recheck = true;
+ tbmres->blockno = chunk_blockno;
+ tbmres->ntuples = -1;
+ tbmres->recheck = true;
istate->schunkbit++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
}
@@ -1104,21 +1104,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
int ntuples;
/* scan bitmap to extract individual offset numbers */
- ntuples = tbm_extract_page_tuple(page, output);
- output->blockno = page->blockno;
- output->ntuples = ntuples;
- output->recheck = page->recheck;
+ ntuples = tbm_extract_page_tuple(page, tbmres);
+ tbmres->blockno = page->blockno;
+ tbmres->ntuples = ntuples;
+ tbmres->recheck = page->recheck;
istate->spageptr++;
LWLockRelease(&istate->lock);
- return output;
+ return;
}
LWLockRelease(&istate->lock);
/* Nothing more in the bitmap */
- return NULL;
+ tbmres->blockno = InvalidBlockNumber;
+ return;
}
/*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 3013a44bae..3b432263bb 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
/* for a partial-match or full-scan query, we accumulate all TIDs here */
TIDBitmap *matchBitmap;
TBMIterator *matchIterator;
- TBMIterateResult *matchResult;
+ TBMIterateResult matchResult;
/* used for Posting list and one page in Posting tree */
ItemPointerData *list;
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 432fae5296..f000c1af28 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
extern void tbm_end_iterate(TBMIterator *iterator);
extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
--
2.40.1
--7mdtsjmrzitrgzgx
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v9-0013-Push-BitmapHeapScan-prefetch-code-into-heapam.c.patch"
^ permalink raw reply [nested|flat] 19+ messages in thread
* Re: RepOrigin vs. replorigin
@ 2026-01-27 22:23 Chao Li <[email protected]>
0 siblings, 1 reply; 19+ messages in thread
From: Chao Li @ 2026-01-27 22:23 UTC (permalink / raw)
To: Masahiko Sawada <[email protected]>; +Cc: Peter Eisentraut <[email protected]>; Amit Kapila <[email protected]>; PostgreSQL Hackers <[email protected]>
> On Jan 28, 2026, at 03:43, Masahiko Sawada <[email protected]> wrote:
>
> On Tue, Jan 27, 2026 at 8:15 AM Peter Eisentraut <[email protected]> wrote:
>>
>> On 27.01.26 12:02, Amit Kapila wrote:
>>> On Tue, Jan 27, 2026 at 2:55 AM Masahiko Sawada <[email protected]> wrote:
>>>>
>>>> While reading the code in origin.c, I found the inconsistent use of
>>>> RepOrigin and replorigin (with an 'l') quite confusing -- especially
>>>> when trying to determine names for new functions or variables. For
>>>> instance,
>>>>
>>>> - RepOriginId
>>>> - InvalidRepOriginId
>>>>
>>>> - RM_REPLORIGIN_ID
>>>> - XLOG_REPLORIGIN_{SET|DROP}
>>>> - replorigin_session_origin
>>>> - replorigin_session_xxx() functions
>>>>
>>>> Is there a conventional rule for choosing one over the other depending
>>>> on context? Or should we consider unifying these naming conventions?"
>>>>
>>>
>>> AFAICS, most places use replorigin. So, +1 to unify the naming by
>>> adding 'l' to places where it is not there unless someone sees a
>>> theory/reason to keep them different.
>>
>> agreed
>>
>
> Thank you for the comments! I agree to unify the naming.
>
> I'm going to push the attached patch, barring any objections.
>
> Regards,
>
> --
> Masahiko Sawada
> Amazon Web Services: https://aws.amazon.com
> <v1-0001-Standardize-replication-origin-naming-to-use-Repl.patch>
This patch is a pure rename from RepOriginId/InvalidRepOriginId to ReplOriginId/InvalidReplOriginId. I applied it locally, build passed, “make check” passed. And I searched over the source tree for any missing replacement and found none. So, LGTM.
Best regards,
--
Chao Li (Evan)
HighGo Software Co., Ltd.
https://www.highgo.com/
^ permalink raw reply [nested|flat] 19+ messages in thread
* Re: RepOrigin vs. replorigin
@ 2026-01-28 20:55 Masahiko Sawada <[email protected]>
parent: Chao Li <[email protected]>
0 siblings, 0 replies; 19+ messages in thread
From: Masahiko Sawada @ 2026-01-28 20:55 UTC (permalink / raw)
To: Chao Li <[email protected]>; +Cc: Peter Eisentraut <[email protected]>; Amit Kapila <[email protected]>; PostgreSQL Hackers <[email protected]>
On Tue, Jan 27, 2026 at 2:24 PM Chao Li <[email protected]> wrote:
>
>
>
> > On Jan 28, 2026, at 03:43, Masahiko Sawada <[email protected]> wrote:
> >
> > On Tue, Jan 27, 2026 at 8:15 AM Peter Eisentraut <[email protected]> wrote:
> >>
> >> On 27.01.26 12:02, Amit Kapila wrote:
> >>> On Tue, Jan 27, 2026 at 2:55 AM Masahiko Sawada <[email protected]> wrote:
> >>>>
> >>>> While reading the code in origin.c, I found the inconsistent use of
> >>>> RepOrigin and replorigin (with an 'l') quite confusing -- especially
> >>>> when trying to determine names for new functions or variables. For
> >>>> instance,
> >>>>
> >>>> - RepOriginId
> >>>> - InvalidRepOriginId
> >>>>
> >>>> - RM_REPLORIGIN_ID
> >>>> - XLOG_REPLORIGIN_{SET|DROP}
> >>>> - replorigin_session_origin
> >>>> - replorigin_session_xxx() functions
> >>>>
> >>>> Is there a conventional rule for choosing one over the other depending
> >>>> on context? Or should we consider unifying these naming conventions?"
> >>>>
> >>>
> >>> AFAICS, most places use replorigin. So, +1 to unify the naming by
> >>> adding 'l' to places where it is not there unless someone sees a
> >>> theory/reason to keep them different.
> >>
> >> agreed
> >>
> >
> > Thank you for the comments! I agree to unify the naming.
> >
> > I'm going to push the attached patch, barring any objections.
> >
> > Regards,
> >
> > --
> > Masahiko Sawada
> > Amazon Web Services: https://aws.amazon.com
> > <v1-0001-Standardize-replication-origin-naming-to-use-Repl.patch>
>
> This patch is a pure rename from RepOriginId/InvalidRepOriginId to ReplOriginId/InvalidReplOriginId. I applied it locally, build passed, “make check” passed. And I searched over the source tree for any missing replacement and found none. So, LGTM.
>
Thank you for reviewing the patch. Pushed.
Regards,
--
Masahiko Sawada
Amazon Web Services: https://aws.amazon.com
^ permalink raw reply [nested|flat] 19+ messages in thread
end of thread, other threads:[~2026-01-28 20:55 UTC | newest]
Thread overview: 19+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2024-02-16 02:23 [PATCH v10 13/17] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v6 12/14] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v11 13/17] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v7 11/13] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v9 12/17] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v11 13/17] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v7 11/13] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v12 13/17] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v9 12/17] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v8 12/17] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v6 12/14] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v8 12/17] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v9 12/17] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v10 13/17] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v6 12/14] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v8 12/17] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2024-02-16 02:23 [PATCH v7 11/13] Separate TBM[Shared]Iterator and TBMIterateResult Melanie Plageman <[email protected]>
2026-01-27 22:23 Re: RepOrigin vs. replorigin Chao Li <[email protected]>
2026-01-28 20:55 ` Re: RepOrigin vs. replorigin Masahiko Sawada <[email protected]>
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox