database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-11-06 07:49:08 +03:00
Code Activity

Merge prune, freeze and vacuum WAL record formats

Browse Source 
The new combined WAL record is now used for pruning, freezing and 2nd
pass of vacuum. This is in preparation for changing VACUUM to write a
combined prune+freeze record per page, instead of separate two
records. The new WAL record format now supports that, but the code
still always writes separate records for pruning and freezing.

This reserves separate XLOG_HEAP2_* info codes for when the pruning
record is emitted for on-access pruning or VACUUM, per Peter
Geoghegan's suggestion. The record format is identical, but having
separate info codes makes it easier analyze pruning and vacuuming with
pg_waldump.

The function to emit the new WAL record, log_heap_prune_and_freeze(),
is in pruneheap.c. The existing heap_log_freeze_plan() and its
subroutines are moved to pruneheap.c without changes, to keep them
together with log_heap_prune_and_freeze().

Author: Melanie Plageman <melanieplageman@gmail.com>
Discussion: https://www.postgresql.org/message-id/CAAKRu_azf-zH%3DDgVbquZ3tFWjMY1w5pO8m-TXJaMdri8z3933g@mail.gmail.com
Discussion: https://www.postgresql.org/message-id/CAAKRu_b2oE4GL%3Dq4g9mcByS9yT7wTQvEH9OLpabj28e%2BWKFi2A@mail.gmail.com
This commit is contained in:
Heikki Linnakangas
2024-03-25 14:59:58 +02:00
parent d44032d014
commit f83d709760
11 changed files with 799 additions and 594 deletions
Download Patch File Download Diff File Expand all files Collapse all files

473
src/backend/access/heap/heapam.c
View File

@@ -91,9 +91,6 @@ static void compute_new_xmax_infomask(TransactionId xmax, uint16 old_infomask,
static TM_Result heap_lock_updated_tuple(Relation rel, HeapTuple tuple,
ItemPointer ctid, TransactionId xid,
LockTupleMode mode);
static int heap_log_freeze_plan(HeapTupleFreeze *tuples, int ntuples,
xl_heap_freeze_plan *plans_out,
OffsetNumber *offsets_out);
static void GetMultiXactIdHintBits(MultiXactId multi, uint16 *new_infomask,
uint16 *new_infomask2);
static TransactionId MultiXactIdGetUpdateXid(TransactionId xmax,
@@ -6746,179 +6743,18 @@ heap_freeze_execute_prepared(Relation rel, Buffer buffer,
/* Now WAL-log freezing if necessary */
if (RelationNeedsWAL(rel))
{
xl_heap_freeze_plan plans[MaxHeapTuplesPerPage];
OffsetNumber offsets[MaxHeapTuplesPerPage];
int nplans;
xl_heap_freeze_page xlrec;
XLogRecPtr recptr;
/* Prepare deduplicated representation for use in WAL record */
nplans = heap_log_freeze_plan(tuples, ntuples, plans, offsets);
xlrec.snapshotConflictHorizon = snapshotConflictHorizon;
xlrec.isCatalogRel = RelationIsAccessibleInLogicalDecoding(rel);
xlrec.nplans = nplans;
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, SizeOfHeapFreezePage);
/*
* The freeze plan array and offset array are not actually in the
* buffer, but pretend that they are. When XLogInsert stores the
* whole buffer, the arrays need not be stored too.
*/
XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
XLogRegisterBufData(0, (char *) plans,
nplans * sizeof(xl_heap_freeze_plan));
XLogRegisterBufData(0, (char *) offsets,
ntuples * sizeof(OffsetNumber));
recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_FREEZE_PAGE);
PageSetLSN(page, recptr);
log_heap_prune_and_freeze(rel, buffer, snapshotConflictHorizon,
false, /* no cleanup lock required */
PRUNE_VACUUM_SCAN,
tuples, ntuples,
NULL, 0, /* redirected */
NULL, 0, /* dead */
NULL, 0); /* unused */
}
END_CRIT_SECTION();
}
/*
* Comparator used to deduplicate XLOG_HEAP2_FREEZE_PAGE freeze plans
*/
static int
heap_log_freeze_cmp(const void *arg1, const void *arg2)
{
HeapTupleFreeze *frz1 = (HeapTupleFreeze *) arg1;
HeapTupleFreeze *frz2 = (HeapTupleFreeze *) arg2;
if (frz1->xmax < frz2->xmax)
return -1;
else if (frz1->xmax > frz2->xmax)
return 1;
if (frz1->t_infomask2 < frz2->t_infomask2)
return -1;
else if (frz1->t_infomask2 > frz2->t_infomask2)
return 1;
if (frz1->t_infomask < frz2->t_infomask)
return -1;
else if (frz1->t_infomask > frz2->t_infomask)
return 1;
if (frz1->frzflags < frz2->frzflags)
return -1;
else if (frz1->frzflags > frz2->frzflags)
return 1;
/*
* heap_log_freeze_eq would consider these tuple-wise plans to be equal.
* (So the tuples will share a single canonical freeze plan.)
*
* We tiebreak on page offset number to keep each freeze plan's page
* offset number array individually sorted. (Unnecessary, but be tidy.)
*/
if (frz1->offset < frz2->offset)
return -1;
else if (frz1->offset > frz2->offset)
return 1;
Assert(false);
return 0;
}
/*
* Compare fields that describe actions required to freeze tuple with caller's
* open plan. If everything matches then the frz tuple plan is equivalent to
* caller's plan.
*/
static inline bool
heap_log_freeze_eq(xl_heap_freeze_plan *plan, HeapTupleFreeze *frz)
{
if (plan->xmax == frz->xmax &&
plan->t_infomask2 == frz->t_infomask2 &&
plan->t_infomask == frz->t_infomask &&
plan->frzflags == frz->frzflags)
return true;
/* Caller must call heap_log_freeze_new_plan again for frz */
return false;
}
/*
* Start new plan initialized using tuple-level actions. At least one tuple
* will have steps required to freeze described by caller's plan during REDO.
*/
static inline void
heap_log_freeze_new_plan(xl_heap_freeze_plan *plan, HeapTupleFreeze *frz)
{
plan->xmax = frz->xmax;
plan->t_infomask2 = frz->t_infomask2;
plan->t_infomask = frz->t_infomask;
plan->frzflags = frz->frzflags;
plan->ntuples = 1; /* for now */
}
/*
* Deduplicate tuple-based freeze plans so that each distinct set of
* processing steps is only stored once in XLOG_HEAP2_FREEZE_PAGE records.
* Called during original execution of freezing (for logged relations).
*
* Return value is number of plans set in *plans_out for caller. Also writes
* an array of offset numbers into *offsets_out output argument for caller
* (actually there is one array per freeze plan, but that's not of immediate
* concern to our caller).
*/
static int
heap_log_freeze_plan(HeapTupleFreeze *tuples, int ntuples,
xl_heap_freeze_plan *plans_out,
OffsetNumber *offsets_out)
{
int nplans = 0;
/* Sort tuple-based freeze plans in the order required to deduplicate */
qsort(tuples, ntuples, sizeof(HeapTupleFreeze), heap_log_freeze_cmp);
for (int i = 0; i < ntuples; i++)
{
HeapTupleFreeze *frz = tuples + i;
if (i == 0)
{
/* New canonical freeze plan starting with first tup */
heap_log_freeze_new_plan(plans_out, frz);
nplans++;
}
else if (heap_log_freeze_eq(plans_out, frz))
{
/* tup matches open canonical plan -- include tup in it */
Assert(offsets_out[i - 1] < frz->offset);
plans_out->ntuples++;
}
else
{
/* Tup doesn't match current plan -- done with it now */
plans_out++;
/* New canonical freeze plan starting with this tup */
heap_log_freeze_new_plan(plans_out, frz);
nplans++;
}
/*
* Save page offset number in dedicated buffer in passing.
*
* REDO routine relies on the record's offset numbers array grouping
* offset numbers by freeze plan. The sort order within each grouping
* is ascending offset number order, just to keep things tidy.
*/
offsets_out[i] = frz->offset;
}
Assert(nplans > 0 && nplans <= ntuples);
return nplans;
}
/*
* heap_freeze_tuple
* Freeze tuple in place, without WAL logging.
@@ -7892,10 +7728,10 @@ heap_index_delete_tuples(Relation rel, TM_IndexDeleteOp *delstate)
* must have considered the original tuple header as part of
* generating its own snapshotConflictHorizon value.
*
* Relying on XLOG_HEAP2_PRUNE records like this is the same
* strategy that index vacuuming uses in all cases. Index VACUUM
* WAL records don't even have a snapshotConflictHorizon field of
* their own for this reason.
* Relying on XLOG_HEAP2_PRUNE_VACUUM_SCAN records like this is
* the same strategy that index vacuuming uses in all cases. Index
* VACUUM WAL records don't even have a snapshotConflictHorizon
* field of their own for this reason.
*/
if (!ItemIdIsNormal(lp))
break;
@@ -8753,64 +8589,119 @@ ExtractReplicaIdentity(Relation relation, HeapTuple tp, bool key_required,
}
/*
* Handles XLOG_HEAP2_PRUNE record type.
*
* Acquires a full cleanup lock.
* Replay XLOG_HEAP2_PRUNE_* records.
*/
static void
heap_xlog_prune(XLogReaderState *record)
heap_xlog_prune_freeze(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_heap_prune *xlrec = (xl_heap_prune *) XLogRecGetData(record);
char *maindataptr = XLogRecGetData(record);
xl_heap_prune xlrec;
Buffer buffer;
RelFileLocator rlocator;
BlockNumber blkno;
XLogRedoAction action;
XLogRecGetBlockTag(record, 0, &rlocator, NULL, &blkno);
memcpy(&xlrec, maindataptr, SizeOfHeapPrune);
maindataptr += SizeOfHeapPrune;
/*
* We're about to remove tuples. In Hot Standby mode, ensure that there's
* no queries running for which the removed tuples are still visible.
* We will take an ordinary exclusive lock or a cleanup lock depending on
* whether the XLHP_CLEANUP_LOCK flag is set. With an ordinary exclusive
* lock, we better not be doing anything that requires moving existing
* tuple data.
*/
if (InHotStandby)
ResolveRecoveryConflictWithSnapshot(xlrec->snapshotConflictHorizon,
xlrec->isCatalogRel,
rlocator);
Assert((xlrec.flags & XLHP_CLEANUP_LOCK) != 0 ||
(xlrec.flags & (XLHP_HAS_REDIRECTIONS | XLHP_HAS_DEAD_ITEMS)) == 0);
/*
* If we have a full-page image, restore it (using a cleanup lock) and
* we're done.
* We are about to remove and/or freeze tuples. In Hot Standby mode,
* ensure that there are no queries running for which the removed tuples
* are still visible or which still consider the frozen xids as running.
* The conflict horizon XID comes after xl_heap_prune.
*/
action = XLogReadBufferForRedoExtended(record, 0, RBM_NORMAL, true,
if ((xlrec.flags & XLHP_HAS_CONFLICT_HORIZON) != 0)
{
TransactionId snapshot_conflict_horizon;
/* memcpy() because snapshot_conflict_horizon is stored unaligned */
memcpy(&snapshot_conflict_horizon, maindataptr, sizeof(TransactionId));
maindataptr += sizeof(TransactionId);
if (InHotStandby)
ResolveRecoveryConflictWithSnapshot(snapshot_conflict_horizon,
(xlrec.flags & XLHP_IS_CATALOG_REL) != 0,
rlocator);
}
/*
* If we have a full-page image, restore it and we're done.
*/
action = XLogReadBufferForRedoExtended(record, 0, RBM_NORMAL,
(xlrec.flags & XLHP_CLEANUP_LOCK) != 0,
&buffer);
if (action == BLK_NEEDS_REDO)
{
Page page = (Page) BufferGetPage(buffer);
OffsetNumber *end;
OffsetNumber *redirected;
OffsetNumber *nowdead;
OffsetNumber *nowunused;
int nredirected;
int ndead;
int nunused;
int nplans;
Size datalen;
xlhp_freeze_plan *plans;
OffsetNumber *frz_offsets;
char *dataptr = XLogRecGetBlockData(record, 0, &datalen);
redirected = (OffsetNumber *) XLogRecGetBlockData(record, 0, &datalen);
heap_xlog_deserialize_prune_and_freeze(dataptr, xlrec.flags,
&nplans, &plans, &frz_offsets,
&nredirected, &redirected,
&ndead, &nowdead,
&nunused, &nowunused);
nredirected = xlrec->nredirected;
ndead = xlrec->ndead;
end = (OffsetNumber *) ((char *) redirected + datalen);
nowdead = redirected + (nredirected * 2);
nowunused = nowdead + ndead;
nunused = (end - nowunused);
Assert(nunused >= 0);
/*
* Update all line pointers per the record, and repair fragmentation
* if needed.
*/
if (nredirected > 0 || ndead > 0 || nunused > 0)
heap_page_prune_execute(buffer,
(xlrec.flags & XLHP_CLEANUP_LOCK) == 0,
redirected, nredirected,
nowdead, ndead,
nowunused, nunused);
/* Update all line pointers per the record, and repair fragmentation */
heap_page_prune_execute(buffer,
redirected, nredirected,
nowdead, ndead,
nowunused, nunused);
/* Freeze tuples */
for (int p = 0; p < nplans; p++)
{
HeapTupleFreeze frz;
/*
* Convert freeze plan representation from WAL record into
* per-tuple format used by heap_execute_freeze_tuple
*/
frz.xmax = plans[p].xmax;
frz.t_infomask2 = plans[p].t_infomask2;
frz.t_infomask = plans[p].t_infomask;
frz.frzflags = plans[p].frzflags;
frz.offset = InvalidOffsetNumber; /* unused, but be tidy */
for (int i = 0; i < plans[p].ntuples; i++)
{
OffsetNumber offset = *(frz_offsets++);
ItemId lp;
HeapTupleHeader tuple;
lp = PageGetItemId(page, offset);
tuple = (HeapTupleHeader) PageGetItem(page, lp);
heap_execute_freeze_tuple(tuple, &frz);
}
}
/* There should be no more data */
Assert((char *) frz_offsets == dataptr + datalen);
/*
* Note: we don't worry about updating the page's prunability hints.
@@ -8821,94 +8712,26 @@ heap_xlog_prune(XLogReaderState *record)
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
{
Size freespace = PageGetHeapFreeSpace(BufferGetPage(buffer));
UnlockReleaseBuffer(buffer);
/*
* After pruning records from a page, it's useful to update the FSM
* about it, as it may cause the page become target for insertions
* later even if vacuum decides not to visit it (which is possible if
* gets marked all-visible.)
*
* Do this regardless of a full-page image being applied, since the
* FSM data is not in the page anyway.
*/
XLogRecordPageWithFreeSpace(rlocator, blkno, freespace);
}
}
/*
* Handles XLOG_HEAP2_VACUUM record type.
*
* Acquires an ordinary exclusive lock only.
*/
static void
heap_xlog_vacuum(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_heap_vacuum *xlrec = (xl_heap_vacuum *) XLogRecGetData(record);
Buffer buffer;
BlockNumber blkno;
XLogRedoAction action;
/*
* If we have a full-page image, restore it (without using a cleanup lock)
* and we're done.
* If we released any space or line pointers, update the free space map.
*
* Do this regardless of a full-page image being applied, since the FSM
* data is not in the page anyway.
*/
action = XLogReadBufferForRedoExtended(record, 0, RBM_NORMAL, false,
&buffer);
if (action == BLK_NEEDS_REDO)
{
Page page = (Page) BufferGetPage(buffer);
OffsetNumber *nowunused;
Size datalen;
OffsetNumber *offnum;
nowunused = (OffsetNumber *) XLogRecGetBlockData(record, 0, &datalen);
/* Shouldn't be a record unless there's something to do */
Assert(xlrec->nunused > 0);
/* Update all now-unused line pointers */
offnum = nowunused;
for (int i = 0; i < xlrec->nunused; i++)
{
OffsetNumber off = *offnum++;
ItemId lp = PageGetItemId(page, off);
Assert(ItemIdIsDead(lp) && !ItemIdHasStorage(lp));
ItemIdSetUnused(lp);
}
/* Attempt to truncate line pointer array now */
PageTruncateLinePointerArray(page);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
{
Size freespace = PageGetHeapFreeSpace(BufferGetPage(buffer));
RelFileLocator rlocator;
if (xlrec.flags & (XLHP_HAS_REDIRECTIONS |
XLHP_HAS_DEAD_ITEMS |
XLHP_HAS_NOW_UNUSED_ITEMS))
{
Size freespace = PageGetHeapFreeSpace(BufferGetPage(buffer));
XLogRecGetBlockTag(record, 0, &rlocator, NULL, &blkno);
UnlockReleaseBuffer(buffer);
UnlockReleaseBuffer(buffer);
/*
* After vacuuming LP_DEAD items from a page, it's useful to update
* the FSM about it, as it may cause the page become target for
* insertions later even if vacuum decides not to visit it (which is
* possible if gets marked all-visible.)
*
* Do this regardless of a full-page image being applied, since the
* FSM data is not in the page anyway.
*/
XLogRecordPageWithFreeSpace(rlocator, blkno, freespace);
XLogRecordPageWithFreeSpace(rlocator, blkno, freespace);
}
else
UnlockReleaseBuffer(buffer);
}
}
@@ -9049,74 +8872,6 @@ heap_xlog_visible(XLogReaderState *record)
UnlockReleaseBuffer(vmbuffer);
}
/*
* Replay XLOG_HEAP2_FREEZE_PAGE records
*/
static void
heap_xlog_freeze_page(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_heap_freeze_page *xlrec = (xl_heap_freeze_page *) XLogRecGetData(record);
Buffer buffer;
/*
* In Hot Standby mode, ensure that there's no queries running which still
* consider the frozen xids as running.
*/
if (InHotStandby)
{
RelFileLocator rlocator;
XLogRecGetBlockTag(record, 0, &rlocator, NULL, NULL);
ResolveRecoveryConflictWithSnapshot(xlrec->snapshotConflictHorizon,
xlrec->isCatalogRel,
rlocator);
}
if (XLogReadBufferForRedo(record, 0, &buffer) == BLK_NEEDS_REDO)
{
Page page = BufferGetPage(buffer);
xl_heap_freeze_plan *plans;
OffsetNumber *offsets;
int curoff = 0;
plans = (xl_heap_freeze_plan *) XLogRecGetBlockData(record, 0, NULL);
offsets = (OffsetNumber *) ((char *) plans +
(xlrec->nplans *
sizeof(xl_heap_freeze_plan)));
for (int p = 0; p < xlrec->nplans; p++)
{
HeapTupleFreeze frz;
/*
* Convert freeze plan representation from WAL record into
* per-tuple format used by heap_execute_freeze_tuple
*/
frz.xmax = plans[p].xmax;
frz.t_infomask2 = plans[p].t_infomask2;
frz.t_infomask = plans[p].t_infomask;
frz.frzflags = plans[p].frzflags;
frz.offset = InvalidOffsetNumber; /* unused, but be tidy */
for (int i = 0; i < plans[p].ntuples; i++)
{
OffsetNumber offset = offsets[curoff++];
ItemId lp;
HeapTupleHeader tuple;
lp = PageGetItemId(page, offset);
tuple = (HeapTupleHeader) PageGetItem(page, lp);
heap_execute_freeze_tuple(tuple, &frz);
}
}
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
/*
* Given an "infobits" field from an XLog record, set the correct bits in the
* given infomask and infomask2 for the tuple touched by the record.
@@ -10017,14 +9772,10 @@ heap2_redo(XLogReaderState *record)
switch (info & XLOG_HEAP_OPMASK)
{
case XLOG_HEAP2_PRUNE:
heap_xlog_prune(record);
break;
case XLOG_HEAP2_VACUUM:
heap_xlog_vacuum(record);
break;
case XLOG_HEAP2_FREEZE_PAGE:
heap_xlog_freeze_page(record);
case XLOG_HEAP2_PRUNE_ON_ACCESS:
case XLOG_HEAP2_PRUNE_VACUUM_SCAN:
case XLOG_HEAP2_PRUNE_VACUUM_CLEANUP:
heap_xlog_prune_freeze(record);
break;
case XLOG_HEAP2_VISIBLE:
heap_xlog_visible(record);

407
src/backend/access/heap/pruneheap.c
View File

@@ -153,7 +153,7 @@ heap_page_prune_opt(Relation relation, Buffer buffer)
* that during on-access pruning with the current implementation.
*/
heap_page_prune(relation, buffer, vistest, false,
&presult, NULL);
&presult, PRUNE_ON_ACCESS, NULL);
/*
* Report the number of tuples reclaimed to pgstats. This is
@@ -204,6 +204,9 @@ heap_page_prune_opt(Relation relation, Buffer buffer)
* tuples removed and the number of line pointers newly marked LP_DEAD.
* heap_page_prune() is responsible for initializing it.
*
* reason indicates why the pruning is performed. It is included in the WAL
* record for debugging and analysis purposes, but otherwise has no effect.
*
* off_loc is the offset location required by the caller to use in error
* callback.
*/
@@ -212,6 +215,7 @@ heap_page_prune(Relation relation, Buffer buffer,
GlobalVisState *vistest,
bool mark_unused_now,
PruneResult *presult,
PruneReason reason,
OffsetNumber *off_loc)
{
Page page = BufferGetPage(buffer);
@@ -338,7 +342,7 @@ heap_page_prune(Relation relation, Buffer buffer,
* Apply the planned item changes, then repair page fragmentation, and
* update the page's hint bit about whether it has free line pointers.
*/
heap_page_prune_execute(buffer,
heap_page_prune_execute(buffer, false,
prstate.redirected, prstate.nredirected,
prstate.nowdead, prstate.ndead,
prstate.nowunused, prstate.nunused);
@@ -359,44 +363,17 @@ heap_page_prune(Relation relation, Buffer buffer,
MarkBufferDirty(buffer);
/*
* Emit a WAL XLOG_HEAP2_PRUNE record showing what we did
* Emit a WAL XLOG_HEAP2_PRUNE_FREEZE record showing what we did
*/
if (RelationNeedsWAL(relation))
{
xl_heap_prune xlrec;
XLogRecPtr recptr;
xlrec.isCatalogRel = RelationIsAccessibleInLogicalDecoding(relation);
xlrec.snapshotConflictHorizon = prstate.snapshotConflictHorizon;
xlrec.nredirected = prstate.nredirected;
xlrec.ndead = prstate.ndead;
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, SizeOfHeapPrune);
XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
/*
* The OffsetNumber arrays are not actually in the buffer, but we
* pretend that they are. When XLogInsert stores the whole
* buffer, the offset arrays need not be stored too.
*/
if (prstate.nredirected > 0)
XLogRegisterBufData(0, (char *) prstate.redirected,
prstate.nredirected *
sizeof(OffsetNumber) * 2);
if (prstate.ndead > 0)
XLogRegisterBufData(0, (char *) prstate.nowdead,
prstate.ndead * sizeof(OffsetNumber));
if (prstate.nunused > 0)
XLogRegisterBufData(0, (char *) prstate.nowunused,
prstate.nunused * sizeof(OffsetNumber));
recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_PRUNE);
PageSetLSN(BufferGetPage(buffer), recptr);
log_heap_prune_and_freeze(relation, buffer,
prstate.snapshotConflictHorizon,
true, reason,
NULL, 0,
prstate.redirected, prstate.nredirected,
prstate.nowdead, prstate.ndead,
prstate.nowunused, prstate.nunused);
}
}
else
@@ -827,11 +804,16 @@ heap_prune_record_unused(PruneState *prstate, OffsetNumber offnum)
/*
* Perform the actual page changes needed by heap_page_prune.
* It is expected that the caller has a full cleanup lock on the
* buffer.
*
* If 'lp_truncate_only' is set, we are merely marking LP_DEAD line pointers
* as unused, not redirecting or removing anything else. The
* PageRepairFragmentation() call is skipped in that case.
*
* If 'lp_truncate_only' is not set, the caller must hold a cleanup lock on
* the buffer. If it is set, an ordinary exclusive lock suffices.
*/
void
heap_page_prune_execute(Buffer buffer,
heap_page_prune_execute(Buffer buffer, bool lp_truncate_only,
OffsetNumber *redirected, int nredirected,
OffsetNumber *nowdead, int ndead,
OffsetNumber *nowunused, int nunused)
@@ -843,6 +825,9 @@ heap_page_prune_execute(Buffer buffer,
/* Shouldn't be called unless there's something to do */
Assert(nredirected > 0 || ndead > 0 || nunused > 0);
/* If 'lp_truncate_only', we can only remove already-dead line pointers */
Assert(!lp_truncate_only || (nredirected == 0 && ndead == 0));
/* Update all redirected line pointers */
offnum = redirected;
for (int i = 0; i < nredirected; i++)
@@ -941,23 +926,29 @@ heap_page_prune_execute(Buffer buffer,
#ifdef USE_ASSERT_CHECKING
/*
* When heap_page_prune() was called, mark_unused_now may have been
* passed as true, which allows would-be LP_DEAD items to be made
* LP_UNUSED instead. This is only possible if the relation has no
* indexes. If there are any dead items, then mark_unused_now was not
* true and every item being marked LP_UNUSED must refer to a
* heap-only tuple.
*/
if (ndead > 0)
if (lp_truncate_only)
{
Assert(ItemIdHasStorage(lp) && ItemIdIsNormal(lp));
htup = (HeapTupleHeader) PageGetItem(page, lp);
Assert(HeapTupleHeaderIsHeapOnly(htup));
/* Setting LP_DEAD to LP_UNUSED in vacuum's second pass */
Assert(ItemIdIsDead(lp) && !ItemIdHasStorage(lp));
}
else
{
Assert(ItemIdIsUsed(lp));
/*
* When heap_page_prune() was called, mark_unused_now may have
* been passed as true, which allows would-be LP_DEAD items to be
* made LP_UNUSED instead. This is only possible if the relation
* has no indexes. If there are any dead items, then
* mark_unused_now was not true and every item being marked
* LP_UNUSED must refer to a heap-only tuple.
*/
if (ndead > 0)
{
Assert(ItemIdHasStorage(lp) && ItemIdIsNormal(lp));
htup = (HeapTupleHeader) PageGetItem(page, lp);
Assert(HeapTupleHeaderIsHeapOnly(htup));
}
else
Assert(ItemIdIsUsed(lp));
}
#endif
@@ -965,17 +956,22 @@ heap_page_prune_execute(Buffer buffer,
ItemIdSetUnused(lp);
}
/*
* Finally, repair any fragmentation, and update the page's hint bit about
* whether it has free pointers.
*/
PageRepairFragmentation(page);
if (lp_truncate_only)
PageTruncateLinePointerArray(page);
else
{
/*
* Finally, repair any fragmentation, and update the page's hint bit
* about whether it has free pointers.
*/
PageRepairFragmentation(page);
/*
* Now that the page has been modified, assert that redirect items still
* point to valid targets.
*/
page_verify_redirects(page);
/*
* Now that the page has been modified, assert that redirect items
* still point to valid targets.
*/
page_verify_redirects(page);
}
}
@@ -1144,3 +1140,288 @@ heap_get_root_tuples(Page page, OffsetNumber *root_offsets)
}
}
}
/*
* Compare fields that describe actions required to freeze tuple with caller's
* open plan. If everything matches then the frz tuple plan is equivalent to
* caller's plan.
*/
static inline bool
heap_log_freeze_eq(xlhp_freeze_plan *plan, HeapTupleFreeze *frz)
{
if (plan->xmax == frz->xmax &&
plan->t_infomask2 == frz->t_infomask2 &&
plan->t_infomask == frz->t_infomask &&
plan->frzflags == frz->frzflags)
return true;
/* Caller must call heap_log_freeze_new_plan again for frz */
return false;
}
/*
* Comparator used to deduplicate XLOG_HEAP2_FREEZE_PAGE freeze plans
*/
static int
heap_log_freeze_cmp(const void *arg1, const void *arg2)
{
HeapTupleFreeze *frz1 = (HeapTupleFreeze *) arg1;
HeapTupleFreeze *frz2 = (HeapTupleFreeze *) arg2;
if (frz1->xmax < frz2->xmax)
return -1;
else if (frz1->xmax > frz2->xmax)
return 1;
if (frz1->t_infomask2 < frz2->t_infomask2)
return -1;
else if (frz1->t_infomask2 > frz2->t_infomask2)
return 1;
if (frz1->t_infomask < frz2->t_infomask)
return -1;
else if (frz1->t_infomask > frz2->t_infomask)
return 1;
if (frz1->frzflags < frz2->frzflags)
return -1;
else if (frz1->frzflags > frz2->frzflags)
return 1;
/*
* heap_log_freeze_eq would consider these tuple-wise plans to be equal.
* (So the tuples will share a single canonical freeze plan.)
*
* We tiebreak on page offset number to keep each freeze plan's page
* offset number array individually sorted. (Unnecessary, but be tidy.)
*/
if (frz1->offset < frz2->offset)
return -1;
else if (frz1->offset > frz2->offset)
return 1;
Assert(false);
return 0;
}
/*
* Start new plan initialized using tuple-level actions. At least one tuple
* will have steps required to freeze described by caller's plan during REDO.
*/
static inline void
heap_log_freeze_new_plan(xlhp_freeze_plan *plan, HeapTupleFreeze *frz)
{
plan->xmax = frz->xmax;
plan->t_infomask2 = frz->t_infomask2;
plan->t_infomask = frz->t_infomask;
plan->frzflags = frz->frzflags;
plan->ntuples = 1; /* for now */
}
/*
* Deduplicate tuple-based freeze plans so that each distinct set of
* processing steps is only stored once in XLOG_HEAP2_FREEZE_PAGE records.
* Called during original execution of freezing (for logged relations).
*
* Return value is number of plans set in *plans_out for caller. Also writes
* an array of offset numbers into *offsets_out output argument for caller
* (actually there is one array per freeze plan, but that's not of immediate
* concern to our caller).
*/
static int
heap_log_freeze_plan(HeapTupleFreeze *tuples, int ntuples,
xlhp_freeze_plan *plans_out,
OffsetNumber *offsets_out)
{
int nplans = 0;
/* Sort tuple-based freeze plans in the order required to deduplicate */
qsort(tuples, ntuples, sizeof(HeapTupleFreeze), heap_log_freeze_cmp);
for (int i = 0; i < ntuples; i++)
{
HeapTupleFreeze *frz = tuples + i;
if (i == 0)
{
/* New canonical freeze plan starting with first tup */
heap_log_freeze_new_plan(plans_out, frz);
nplans++;
}
else if (heap_log_freeze_eq(plans_out, frz))
{
/* tup matches open canonical plan -- include tup in it */
Assert(offsets_out[i - 1] < frz->offset);
plans_out->ntuples++;
}
else
{
/* Tup doesn't match current plan -- done with it now */
plans_out++;
/* New canonical freeze plan starting with this tup */
heap_log_freeze_new_plan(plans_out, frz);
nplans++;
}
/*
* Save page offset number in dedicated buffer in passing.
*
* REDO routine relies on the record's offset numbers array grouping
* offset numbers by freeze plan. The sort order within each grouping
* is ascending offset number order, just to keep things tidy.
*/
offsets_out[i] = frz->offset;
}
Assert(nplans > 0 && nplans <= ntuples);
return nplans;
}
/*
* Write an XLOG_HEAP2_PRUNE_FREEZE WAL record
*
* This is used for several different page maintenance operations:
*
* - Page pruning, in VACUUM's 1st pass or on access: Some items are
* redirected, some marked dead, and some removed altogether.
*
* - Freezing: Items are marked as 'frozen'.
*
* - Vacuum, 2nd pass: Items that are already LP_DEAD are marked as unused.
*
* They have enough commonalities that we use a single WAL record for them
* all.
*
* If replaying the record requires a cleanup lock, pass cleanup_lock = true.
* Replaying 'redirected' or 'dead' items always requires a cleanup lock, but
* replaying 'unused' items depends on whether they were all previously marked
* as dead.
*
* Note: This function scribbles on the 'frozen' array.
*
* Note: This is called in a critical section, so careful what you do here.
*/
void
log_heap_prune_and_freeze(Relation relation, Buffer buffer,
TransactionId conflict_xid,
bool cleanup_lock,
PruneReason reason,
HeapTupleFreeze *frozen, int nfrozen,
OffsetNumber *redirected, int nredirected,
OffsetNumber *dead, int ndead,
OffsetNumber *unused, int nunused)
{
xl_heap_prune xlrec;
XLogRecPtr recptr;
uint8 info;
/* The following local variables hold data registered in the WAL record: */
xlhp_freeze_plan plans[MaxHeapTuplesPerPage];
xlhp_freeze_plans freeze_plans;
xlhp_prune_items redirect_items;
xlhp_prune_items dead_items;
xlhp_prune_items unused_items;
OffsetNumber frz_offsets[MaxHeapTuplesPerPage];
xlrec.flags = 0;
/*
* Prepare data for the buffer. The arrays are not actually in the
* buffer, but we pretend that they are. When XLogInsert stores a full
* page image, the arrays can be omitted.
*/
XLogBeginInsert();
XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
if (nfrozen > 0)
{
int nplans;
xlrec.flags |= XLHP_HAS_FREEZE_PLANS;
/*
* Prepare deduplicated representation for use in the WAL record. This
* destructively sorts frozen tuples array in-place.
*/
nplans = heap_log_freeze_plan(frozen, nfrozen, plans, frz_offsets);
freeze_plans.nplans = nplans;
XLogRegisterBufData(0, (char *) &freeze_plans,
offsetof(xlhp_freeze_plans, plans));
XLogRegisterBufData(0, (char *) plans,
sizeof(xlhp_freeze_plan) * nplans);
}
if (nredirected > 0)
{
xlrec.flags |= XLHP_HAS_REDIRECTIONS;
redirect_items.ntargets = nredirected;
XLogRegisterBufData(0, (char *) &redirect_items,
offsetof(xlhp_prune_items, data));
XLogRegisterBufData(0, (char *) redirected,
sizeof(OffsetNumber[2]) * nredirected);
}
if (ndead > 0)
{
xlrec.flags |= XLHP_HAS_DEAD_ITEMS;
dead_items.ntargets = ndead;
XLogRegisterBufData(0, (char *) &dead_items,
offsetof(xlhp_prune_items, data));
XLogRegisterBufData(0, (char *) dead,
sizeof(OffsetNumber) * ndead);
}
if (nunused > 0)
{
xlrec.flags |= XLHP_HAS_NOW_UNUSED_ITEMS;
unused_items.ntargets = nunused;
XLogRegisterBufData(0, (char *) &unused_items,
offsetof(xlhp_prune_items, data));
XLogRegisterBufData(0, (char *) unused,
sizeof(OffsetNumber) * nunused);
}
if (nfrozen > 0)
XLogRegisterBufData(0, (char *) frz_offsets,
sizeof(OffsetNumber) * nfrozen);
/*
* Prepare the main xl_heap_prune record. We already set the XLPH_HAS_*
* flag above.
*/
if (RelationIsAccessibleInLogicalDecoding(relation))
xlrec.flags |= XLHP_IS_CATALOG_REL;
if (TransactionIdIsValid(conflict_xid))
xlrec.flags |= XLHP_HAS_CONFLICT_HORIZON;
if (cleanup_lock)
xlrec.flags |= XLHP_CLEANUP_LOCK;
else
{
Assert(nredirected == 0 && ndead == 0);
/* also, any items in 'unused' must've been LP_DEAD previously */
}
XLogRegisterData((char *) &xlrec, SizeOfHeapPrune);
if (TransactionIdIsValid(conflict_xid))
XLogRegisterData((char *) &conflict_xid, sizeof(TransactionId));
switch (reason)
{
case PRUNE_ON_ACCESS:
info = XLOG_HEAP2_PRUNE_ON_ACCESS;
break;
case PRUNE_VACUUM_SCAN:
info = XLOG_HEAP2_PRUNE_VACUUM_SCAN;
break;
case PRUNE_VACUUM_CLEANUP:
info = XLOG_HEAP2_PRUNE_VACUUM_CLEANUP;
break;
default:
elog(ERROR, "unrecognized prune reason: %d", (int) reason);
break;
}
recptr = XLogInsert(RM_HEAP2_ID, info);
PageSetLSN(BufferGetPage(buffer), recptr);
}

24
src/backend/access/heap/vacuumlazy.c
View File

@@ -1462,7 +1462,7 @@ lazy_scan_prune(LVRelState *vacrel,
* false otherwise.
*/
heap_page_prune(rel, buf, vacrel->vistest, vacrel->nindexes == 0,
&presult, &vacrel->offnum);
&presult, PRUNE_VACUUM_SCAN, &vacrel->offnum);
/*
* We will update the VM after collecting LP_DEAD items and freezing
@@ -2546,20 +2546,14 @@ lazy_vacuum_heap_page(LVRelState *vacrel, BlockNumber blkno, Buffer buffer,
/* XLOG stuff */
if (RelationNeedsWAL(vacrel->rel))
{
xl_heap_vacuum xlrec;
XLogRecPtr recptr;
xlrec.nunused = nunused;
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, SizeOfHeapVacuum);
XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
XLogRegisterBufData(0, (char *) unused, nunused * sizeof(OffsetNumber));
recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_VACUUM);
PageSetLSN(page, recptr);
log_heap_prune_and_freeze(vacrel->rel, buffer,
InvalidTransactionId,
false, /* no cleanup lock required */
PRUNE_VACUUM_CLEANUP,
NULL, 0, /* frozen */
NULL, 0, /* redirected */
NULL, 0, /* dead */
unused, nunused);
}
/*