Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorThomas Munro2023-09-05 06:26:12 +0000
committerThomas Munro2023-09-05 07:53:43 +0000
commitf691f5b80a85c66d715b4340ffabb503eb19393e (patch)
tree26a06c87096de2f9571956b4370ccbf1852d4cba /src/backend
parentaa0d3504560d40f4300a3d49d1c6c3bfc3b894e5 (diff)
Remove the "snapshot too old" feature.
Remove the old_snapshot_threshold setting and mechanism for producing the error "snapshot too old", originally added by commit 848ef42b. Unfortunately it had a number of known problems in terms of correctness and performance, mostly reported by Andres in the course of his work on snapshot scalability. We agreed to remove it, after a long period without an active plan to fix it. This is certainly a desirable feature, and someone might propose a new or improved implementation in the future. Reported-by: Andres Freund <andres@anarazel.de> Discussion: https://postgr.es/m/CACG%3DezYV%2BEvO135fLRdVn-ZusfVsTY6cH1OZqWtezuEYH6ciQA%40mail.gmail.com Discussion: https://postgr.es/m/20200401064008.qob7bfnnbu4w5cw4%40alap3.anarazel.de Discussion: https://postgr.es/m/CA%2BTgmoY%3Daqf0zjTD%2B3dUWYkgMiNDegDLFjo%2B6ze%3DWtpik%2B3XqA%40mail.gmail.com
Diffstat (limited to 'src/backend')
-rw-r--r--src/backend/access/brin/brin_revmap.c7
-rw-r--r--src/backend/access/gin/ginbtree.c2
-rw-r--r--src/backend/access/gin/ginget.c4
-rw-r--r--src/backend/access/gist/gistget.c1
-rw-r--r--src/backend/access/hash/hashsearch.c6
-rw-r--r--src/backend/access/heap/heapam.c9
-rw-r--r--src/backend/access/heap/pruneheap.c120
-rw-r--r--src/backend/access/heap/vacuumlazy.c5
-rw-r--r--src/backend/access/nbtree/nbtsearch.c9
-rw-r--r--src/backend/access/spgist/spgscan.c1
-rw-r--r--src/backend/catalog/index.c28
-rw-r--r--src/backend/commands/vacuum.c19
-rw-r--r--src/backend/storage/buffer/bufmgr.c17
-rw-r--r--src/backend/storage/ipc/ipci.c2
-rw-r--r--src/backend/storage/ipc/procarray.c36
-rw-r--r--src/backend/storage/lmgr/lwlocknames.txt2
-rw-r--r--src/backend/utils/activity/wait_event_names.txt1
-rw-r--r--src/backend/utils/errcodes.txt4
-rw-r--r--src/backend/utils/misc/guc_tables.c11
-rw-r--r--src/backend/utils/misc/postgresql.conf.sample2
-rw-r--r--src/backend/utils/time/snapmgr.c468
21 files changed, 21 insertions, 733 deletions
diff --git a/src/backend/access/brin/brin_revmap.c b/src/backend/access/brin/brin_revmap.c
index 84d627cb5c9..956dd927656 100644
--- a/src/backend/access/brin/brin_revmap.c
+++ b/src/backend/access/brin/brin_revmap.c
@@ -79,7 +79,6 @@ brinRevmapInitialize(Relation idxrel, BlockNumber *pagesPerRange,
meta = ReadBuffer(idxrel, BRIN_METAPAGE_BLKNO);
LockBuffer(meta, BUFFER_LOCK_SHARE);
page = BufferGetPage(meta);
- TestForOldSnapshot(snapshot, idxrel, page);
metadata = (BrinMetaPageData *) PageGetContents(page);
revmap = palloc(sizeof(BrinRevmap));
@@ -277,7 +276,6 @@ brinGetTupleForHeapBlock(BrinRevmap *revmap, BlockNumber heapBlk,
}
LockBuffer(*buf, mode);
page = BufferGetPage(*buf);
- TestForOldSnapshot(snapshot, idxRel, page);
/* If we land on a revmap page, start over */
if (BRIN_IS_REGULAR_PAGE(page))
@@ -372,11 +370,6 @@ brinRevmapDesummarizeRange(Relation idxrel, BlockNumber heapBlk)
LockBuffer(regBuf, BUFFER_LOCK_EXCLUSIVE);
regPg = BufferGetPage(regBuf);
- /*
- * We're only removing data, not reading it, so there's no need to
- * TestForOldSnapshot here.
- */
-
/* if this is no longer a regular page, tell caller to start over */
if (!BRIN_IS_REGULAR_PAGE(regPg))
{
diff --git a/src/backend/access/gin/ginbtree.c b/src/backend/access/gin/ginbtree.c
index 35490c72832..7d097c75e05 100644
--- a/src/backend/access/gin/ginbtree.c
+++ b/src/backend/access/gin/ginbtree.c
@@ -100,7 +100,6 @@ ginFindLeafPage(GinBtree btree, bool searchMode,
stack->off = InvalidOffsetNumber;
page = BufferGetPage(stack->buffer);
- TestForOldSnapshot(snapshot, btree->index, page);
access = ginTraverseLock(stack->buffer, searchMode);
@@ -127,7 +126,6 @@ ginFindLeafPage(GinBtree btree, bool searchMode,
stack->buffer = ginStepRight(stack->buffer, btree->index, access);
stack->blkno = rightlink;
page = BufferGetPage(stack->buffer);
- TestForOldSnapshot(snapshot, btree->index, page);
if (!searchMode && GinPageIsIncompleteSplit(page))
ginFinishSplit(btree, stack, false, NULL);
diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 1f0214498cd..10d2bb89008 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -158,7 +158,6 @@ collectMatchBitmap(GinBtreeData *btree, GinBtreeStack *stack,
return true;
page = BufferGetPage(stack->buffer);
- TestForOldSnapshot(snapshot, btree->index, page);
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, stack->off));
/*
@@ -1460,7 +1459,6 @@ scanGetCandidate(IndexScanDesc scan, pendingPosition *pos)
for (;;)
{
page = BufferGetPage(pos->pendingBuffer);
- TestForOldSnapshot(scan->xs_snapshot, scan->indexRelation, page);
maxoff = PageGetMaxOffsetNumber(page);
if (pos->firstOffset > maxoff)
@@ -1641,7 +1639,6 @@ collectMatchesForHeapRow(IndexScanDesc scan, pendingPosition *pos)
sizeof(bool) * (pos->lastOffset - pos->firstOffset));
page = BufferGetPage(pos->pendingBuffer);
- TestForOldSnapshot(scan->xs_snapshot, scan->indexRelation, page);
for (i = 0; i < so->nkeys; i++)
{
@@ -1844,7 +1841,6 @@ scanPendingInsert(IndexScanDesc scan, TIDBitmap *tbm, int64 *ntids)
LockBuffer(metabuffer, GIN_SHARE);
page = BufferGetPage(metabuffer);
- TestForOldSnapshot(scan->xs_snapshot, scan->indexRelation, page);
blkno = GinPageGetMeta(page)->head;
/*
diff --git a/src/backend/access/gist/gistget.c b/src/backend/access/gist/gistget.c
index e2c9b5f069c..31349174280 100644
--- a/src/backend/access/gist/gistget.c
+++ b/src/backend/access/gist/gistget.c
@@ -346,7 +346,6 @@ gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem,
PredicateLockPage(r, BufferGetBlockNumber(buffer), scan->xs_snapshot);
gistcheckpage(scan->indexRelation, buffer);
page = BufferGetPage(buffer);
- TestForOldSnapshot(scan->xs_snapshot, r, page);
opaque = GistPageGetOpaque(page);
/*
diff --git a/src/backend/access/hash/hashsearch.c b/src/backend/access/hash/hashsearch.c
index 9ea2a42a07f..0a031bfd18f 100644
--- a/src/backend/access/hash/hashsearch.c
+++ b/src/backend/access/hash/hashsearch.c
@@ -71,7 +71,6 @@ _hash_next(IndexScanDesc scan, ScanDirection dir)
if (BlockNumberIsValid(blkno))
{
buf = _hash_getbuf(rel, blkno, HASH_READ, LH_OVERFLOW_PAGE);
- TestForOldSnapshot(scan->xs_snapshot, rel, BufferGetPage(buf));
if (!_hash_readpage(scan, &buf, dir))
end_of_scan = true;
}
@@ -91,7 +90,6 @@ _hash_next(IndexScanDesc scan, ScanDirection dir)
{
buf = _hash_getbuf(rel, blkno, HASH_READ,
LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
- TestForOldSnapshot(scan->xs_snapshot, rel, BufferGetPage(buf));
/*
* We always maintain the pin on bucket page for whole scan
@@ -186,7 +184,6 @@ _hash_readnext(IndexScanDesc scan,
if (block_found)
{
*pagep = BufferGetPage(*bufp);
- TestForOldSnapshot(scan->xs_snapshot, rel, *pagep);
*opaquep = HashPageGetOpaque(*pagep);
}
}
@@ -232,7 +229,6 @@ _hash_readprev(IndexScanDesc scan,
*bufp = _hash_getbuf(rel, blkno, HASH_READ,
LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
*pagep = BufferGetPage(*bufp);
- TestForOldSnapshot(scan->xs_snapshot, rel, *pagep);
*opaquep = HashPageGetOpaque(*pagep);
/*
@@ -351,7 +347,6 @@ _hash_first(IndexScanDesc scan, ScanDirection dir)
buf = _hash_getbucketbuf_from_hashkey(rel, hashkey, HASH_READ, NULL);
PredicateLockPage(rel, BufferGetBlockNumber(buf), scan->xs_snapshot);
page = BufferGetPage(buf);
- TestForOldSnapshot(scan->xs_snapshot, rel, page);
opaque = HashPageGetOpaque(page);
bucket = opaque->hasho_bucket;
@@ -387,7 +382,6 @@ _hash_first(IndexScanDesc scan, ScanDirection dir)
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
old_buf = _hash_getbuf(rel, old_blkno, HASH_READ, LH_BUCKET_PAGE);
- TestForOldSnapshot(scan->xs_snapshot, rel, BufferGetPage(old_buf));
/*
* remember the split bucket buffer so as to use it later for
diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index dc3c4074ed6..88a123d38a6 100644
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -425,7 +425,6 @@ heapgetpage(TableScanDesc sscan, BlockNumber block)
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
- TestForOldSnapshot(snapshot, scan->rs_base.rs_rd, page);
lines = PageGetMaxOffsetNumber(page);
ntup = 0;
@@ -565,8 +564,6 @@ heapgettup_start_page(HeapScanDesc scan, ScanDirection dir, int *linesleft,
/* Caller is responsible for ensuring buffer is locked if needed */
page = BufferGetPage(scan->rs_cbuf);
- TestForOldSnapshot(scan->rs_base.rs_snapshot, scan->rs_base.rs_rd, page);
-
*linesleft = PageGetMaxOffsetNumber(page) - FirstOffsetNumber + 1;
if (ScanDirectionIsForward(dir))
@@ -598,8 +595,6 @@ heapgettup_continue_page(HeapScanDesc scan, ScanDirection dir, int *linesleft,
/* Caller is responsible for ensuring buffer is locked if needed */
page = BufferGetPage(scan->rs_cbuf);
- TestForOldSnapshot(scan->rs_base.rs_snapshot, scan->rs_base.rs_rd, page);
-
if (ScanDirectionIsForward(dir))
{
*lineoff = OffsetNumberNext(scan->rs_coffset);
@@ -864,7 +859,6 @@ heapgettup_pagemode(HeapScanDesc scan,
/* continue from previously returned page/tuple */
block = scan->rs_cblock; /* current page */
page = BufferGetPage(scan->rs_cbuf);
- TestForOldSnapshot(scan->rs_base.rs_snapshot, scan->rs_base.rs_rd, page);
lineindex = scan->rs_cindex + dir;
if (ScanDirectionIsForward(dir))
@@ -884,7 +878,6 @@ heapgettup_pagemode(HeapScanDesc scan,
{
heapgetpage((TableScanDesc) scan, block);
page = BufferGetPage(scan->rs_cbuf);
- TestForOldSnapshot(scan->rs_base.rs_snapshot, scan->rs_base.rs_rd, page);
linesleft = scan->rs_ntuples;
lineindex = ScanDirectionIsForward(dir) ? 0 : linesleft - 1;
@@ -1372,7 +1365,6 @@ heap_fetch(Relation relation,
*/
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
- TestForOldSnapshot(snapshot, relation, page);
/*
* We'd better check for out-of-range offnum in case of VACUUM since the
@@ -1663,7 +1655,6 @@ heap_get_latest_tid(TableScanDesc sscan,
buffer = ReadBuffer(relation, ItemPointerGetBlockNumber(&ctid));
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
- TestForOldSnapshot(snapshot, relation, page);
/*
* Check for bogus item number. This is not treated as an error
diff --git a/src/backend/access/heap/pruneheap.c b/src/backend/access/heap/pruneheap.c
index 47b9e209154..18193efa238 100644
--- a/src/backend/access/heap/pruneheap.c
+++ b/src/backend/access/heap/pruneheap.c
@@ -36,18 +36,6 @@ typedef struct
/* tuple visibility test, initialized for the relation */
GlobalVisState *vistest;
- /*
- * Thresholds set by TransactionIdLimitedForOldSnapshots() if they have
- * been computed (done on demand, and only if
- * OldSnapshotThresholdActive()). The first time a tuple is about to be
- * removed based on the limited horizon, old_snap_used is set to true, and
- * SetOldSnapshotThresholdTimestamp() is called. See
- * heap_prune_satisfies_vacuum().
- */
- TimestampTz old_snap_ts;
- TransactionId old_snap_xmin;
- bool old_snap_used;
-
TransactionId new_prune_xid; /* new prune hint value for page */
TransactionId snapshotConflictHorizon; /* latest xid removed */
int nredirected; /* numbers of entries in arrays below */
@@ -110,8 +98,6 @@ heap_page_prune_opt(Relation relation, Buffer buffer)
Page page = BufferGetPage(buffer);
TransactionId prune_xid;
GlobalVisState *vistest;
- TransactionId limited_xmin = InvalidTransactionId;
- TimestampTz limited_ts = 0;
Size minfree;
/*
@@ -123,15 +109,6 @@ heap_page_prune_opt(Relation relation, Buffer buffer)
return;
/*
- * XXX: Magic to keep old_snapshot_threshold tests appear "working". They
- * currently are broken, and discussion of what to do about them is
- * ongoing. See
- * https://www.postgresql.org/message-id/20200403001235.e6jfdll3gh2ygbuc%40alap3.anarazel.de
- */
- if (old_snapshot_threshold == 0)
- SnapshotTooOldMagicForTest();
-
- /*
* First check whether there's any chance there's something to prune,
* determining the appropriate horizon is a waste if there's no prune_xid
* (i.e. no updates/deletes left potentially dead tuples around).
@@ -143,35 +120,11 @@ heap_page_prune_opt(Relation relation, Buffer buffer)
/*
* Check whether prune_xid indicates that there may be dead rows that can
* be cleaned up.
- *
- * It is OK to check the old snapshot limit before acquiring the cleanup
- * lock because the worst that can happen is that we are not quite as
- * aggressive about the cleanup (by however many transaction IDs are
- * consumed between this point and acquiring the lock). This allows us to
- * save significant overhead in the case where the page is found not to be
- * prunable.
- *
- * Even if old_snapshot_threshold is set, we first check whether the page
- * can be pruned without. Both because
- * TransactionIdLimitedForOldSnapshots() is not cheap, and because not
- * unnecessarily relying on old_snapshot_threshold avoids causing
- * conflicts.
*/
vistest = GlobalVisTestFor(relation);
if (!GlobalVisTestIsRemovableXid(vistest, prune_xid))
- {
- if (!OldSnapshotThresholdActive())
- return;
-
- if (!TransactionIdLimitedForOldSnapshots(GlobalVisTestNonRemovableHorizon(vistest),
- relation,
- &limited_xmin, &limited_ts))
- return;
-
- if (!TransactionIdPrecedes(prune_xid, limited_xmin))
- return;
- }
+ return;
/*
* We prune when a previous UPDATE failed to find enough space on the page
@@ -205,8 +158,8 @@ heap_page_prune_opt(Relation relation, Buffer buffer)
int ndeleted,
nnewlpdead;
- ndeleted = heap_page_prune(relation, buffer, vistest, limited_xmin,
- limited_ts, &nnewlpdead, NULL);
+ ndeleted = heap_page_prune(relation, buffer, vistest,
+ &nnewlpdead, NULL);
/*
* Report the number of tuples reclaimed to pgstats. This is
@@ -249,9 +202,7 @@ heap_page_prune_opt(Relation relation, Buffer buffer)
*
* vistest is used to distinguish whether tuples are DEAD or RECENTLY_DEAD
* (see heap_prune_satisfies_vacuum and
- * HeapTupleSatisfiesVacuum). old_snap_xmin / old_snap_ts need to
- * either have been set by TransactionIdLimitedForOldSnapshots, or
- * InvalidTransactionId/0 respectively.
+ * HeapTupleSatisfiesVacuum).
*
* Sets *nnewlpdead for caller, indicating the number of items that were
* newly set LP_DEAD during prune operation.
@@ -264,8 +215,6 @@ heap_page_prune_opt(Relation relation, Buffer buffer)
int
heap_page_prune(Relation relation, Buffer buffer,
GlobalVisState *vistest,
- TransactionId old_snap_xmin,
- TimestampTz old_snap_ts,
int *nnewlpdead,
OffsetNumber *off_loc)
{
@@ -291,9 +240,6 @@ heap_page_prune(Relation relation, Buffer buffer,
prstate.new_prune_xid = InvalidTransactionId;
prstate.rel = relation;
prstate.vistest = vistest;
- prstate.old_snap_xmin = old_snap_xmin;
- prstate.old_snap_ts = old_snap_ts;
- prstate.old_snap_used = false;
prstate.snapshotConflictHorizon = InvalidTransactionId;
prstate.nredirected = prstate.ndead = prstate.nunused = 0;
memset(prstate.marked, 0, sizeof(prstate.marked));
@@ -481,19 +427,6 @@ heap_page_prune(Relation relation, Buffer buffer,
/*
* Perform visibility checks for heap pruning.
- *
- * This is more complicated than just using GlobalVisTestIsRemovableXid()
- * because of old_snapshot_threshold. We only want to increase the threshold
- * that triggers errors for old snapshots when we actually decide to remove a
- * row based on the limited horizon.
- *
- * Due to its cost we also only want to call
- * TransactionIdLimitedForOldSnapshots() if necessary, i.e. we might not have
- * done so in heap_page_prune_opt() if pd_prune_xid was old enough. But we
- * still want to be able to remove rows that are too new to be removed
- * according to prstate->vistest, but that can be removed based on
- * old_snapshot_threshold. So we call TransactionIdLimitedForOldSnapshots() on
- * demand in here, if appropriate.
*/
static HTSV_Result
heap_prune_satisfies_vacuum(PruneState *prstate, HeapTuple tup, Buffer buffer)
@@ -506,53 +439,8 @@ heap_prune_satisfies_vacuum(PruneState *prstate, HeapTuple tup, Buffer buffer)
if (res != HEAPTUPLE_RECENTLY_DEAD)
return res;
- /*
- * If we are already relying on the limited xmin, there is no need to
- * delay doing so anymore.
- */
- if (prstate->old_snap_used)
- {
- Assert(TransactionIdIsValid(prstate->old_snap_xmin));
-
- if (TransactionIdPrecedes(dead_after, prstate->old_snap_xmin))
- res = HEAPTUPLE_DEAD;
- return res;
- }
-
- /*
- * First check if GlobalVisTestIsRemovableXid() is sufficient to find the
- * row dead. If not, and old_snapshot_threshold is enabled, try to use the
- * lowered horizon.
- */
if (GlobalVisTestIsRemovableXid(prstate->vistest, dead_after))
res = HEAPTUPLE_DEAD;
- else if (OldSnapshotThresholdActive())
- {
- /* haven't determined limited horizon yet, requests */
- if (!TransactionIdIsValid(prstate->old_snap_xmin))
- {
- TransactionId horizon =
- GlobalVisTestNonRemovableHorizon(prstate->vistest);
-
- TransactionIdLimitedForOldSnapshots(horizon, prstate->rel,
- &prstate->old_snap_xmin,
- &prstate->old_snap_ts);
- }
-
- if (TransactionIdIsValid(prstate->old_snap_xmin) &&
- TransactionIdPrecedes(dead_after, prstate->old_snap_xmin))
- {
- /*
- * About to remove row based on snapshot_too_old. Need to raise
- * the threshold so problematic accesses would error.
- */
- Assert(!prstate->old_snap_used);
- SetOldSnapshotThresholdTimestamp(prstate->old_snap_ts,
- prstate->old_snap_xmin);
- prstate->old_snap_used = true;
- res = HEAPTUPLE_DEAD;
- }
- }
return res;
}
diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 6a41ee635d3..1a05adfa61c 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -1588,7 +1588,7 @@ retry:
* that were deleted from indexes.
*/
tuples_deleted = heap_page_prune(rel, buf, vacrel->vistest,
- InvalidTransactionId, 0, &nnewlpdead,
+ &nnewlpdead,
&vacrel->offnum);
/*
@@ -2875,8 +2875,7 @@ should_attempt_truncation(LVRelState *vacrel)
{
BlockNumber possibly_freeable;
- if (!vacrel->do_rel_truncate || VacuumFailsafeActive ||
- old_snapshot_threshold >= 0)
+ if (!vacrel->do_rel_truncate || VacuumFailsafeActive)
return false;
possibly_freeable = vacrel->rel_pages - vacrel->nonempty_pages;
diff --git a/src/backend/access/nbtree/nbtsearch.c b/src/backend/access/nbtree/nbtsearch.c
index 3230b3b8940..1799089fb45 100644
--- a/src/backend/access/nbtree/nbtsearch.c
+++ b/src/backend/access/nbtree/nbtsearch.c
@@ -278,7 +278,6 @@ _bt_moveright(Relation rel,
for (;;)
{
page = BufferGetPage(buf);
- TestForOldSnapshot(snapshot, rel, page);
opaque = BTPageGetOpaque(page);
if (P_RIGHTMOST(opaque))
@@ -2029,7 +2028,6 @@ _bt_readnextpage(IndexScanDesc scan, BlockNumber blkno, ScanDirection dir)
/* step right one page */
so->currPos.buf = _bt_getbuf(rel, blkno, BT_READ);
page = BufferGetPage(so->currPos.buf);
- TestForOldSnapshot(scan->xs_snapshot, rel, page);
opaque = BTPageGetOpaque(page);
/* check for deleted page */
if (!P_IGNORE(opaque))
@@ -2132,7 +2130,6 @@ _bt_readnextpage(IndexScanDesc scan, BlockNumber blkno, ScanDirection dir)
* and do it all again.
*/
page = BufferGetPage(so->currPos.buf);
- TestForOldSnapshot(scan->xs_snapshot, rel, page);
opaque = BTPageGetOpaque(page);
if (!P_IGNORE(opaque))
{
@@ -2238,7 +2235,6 @@ _bt_walk_left(Relation rel, Buffer buf, Snapshot snapshot)
CHECK_FOR_INTERRUPTS();
buf = _bt_getbuf(rel, blkno, BT_READ);
page = BufferGetPage(buf);
- TestForOldSnapshot(snapshot, rel, page);
opaque = BTPageGetOpaque(page);
/*
@@ -2265,14 +2261,12 @@ _bt_walk_left(Relation rel, Buffer buf, Snapshot snapshot)
blkno = opaque->btpo_next;
buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
page = BufferGetPage(buf);
- TestForOldSnapshot(snapshot, rel, page);
opaque = BTPageGetOpaque(page);
}
/* Return to the original page to see what's up */
buf = _bt_relandgetbuf(rel, buf, obknum, BT_READ);
page = BufferGetPage(buf);
- TestForOldSnapshot(snapshot, rel, page);
opaque = BTPageGetOpaque(page);
if (P_ISDELETED(opaque))
{
@@ -2290,7 +2284,6 @@ _bt_walk_left(Relation rel, Buffer buf, Snapshot snapshot)
blkno = opaque->btpo_next;
buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
page = BufferGetPage(buf);
- TestForOldSnapshot(snapshot, rel, page);
opaque = BTPageGetOpaque(page);
if (!P_ISDELETED(opaque))
break;
@@ -2351,7 +2344,6 @@ _bt_get_endpoint(Relation rel, uint32 level, bool rightmost,
return InvalidBuffer;
page = BufferGetPage(buf);
- TestForOldSnapshot(snapshot, rel, page);
opaque = BTPageGetOpaque(page);
for (;;)
@@ -2371,7 +2363,6 @@ _bt_get_endpoint(Relation rel, uint32 level, bool rightmost,
RelationGetRelationName(rel));
buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
page = BufferGetPage(buf);
- TestForOldSnapshot(snapshot, rel, page);
opaque = BTPageGetOpaque(page);
}
diff --git a/src/backend/access/spgist/spgscan.c b/src/backend/access/spgist/spgscan.c
index cbfaf0c00ac..17cab0087fe 100644
--- a/src/backend/access/spgist/spgscan.c
+++ b/src/backend/access/spgist/spgscan.c
@@ -862,7 +862,6 @@ redirect:
/* else new pointer points to the same page, no work needed */
page = BufferGetPage(buffer);
- TestForOldSnapshot(snapshot, index, page);
isnull = SpGistPageStoresNulls(page) ? true : false;
diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c
index fd09378848e..72f476b51de 100644
--- a/src/backend/catalog/index.c
+++ b/src/backend/catalog/index.c
@@ -3048,12 +3048,11 @@ index_build(Relation heapRelation,
/*
* If we found any potentially broken HOT chains, mark the index as not
* being usable until the current transaction is below the event horizon.
- * See src/backend/access/heap/README.HOT for discussion. Also set this
- * if early pruning/vacuuming is enabled for the heap relation. While it
- * might become safe to use the index earlier based on actual cleanup
- * activity and other active transactions, the test for that would be much
- * more complex and would require some form of blocking, so keep it simple
- * and fast by just using the current transaction.
+ * See src/backend/access/heap/README.HOT for discussion. While it might
+ * become safe to use the index earlier based on actual cleanup activity
+ * and other active transactions, the test for that would be much more
+ * complex and would require some form of blocking, so keep it simple and
+ * fast by just using the current transaction.
*
* However, when reindexing an existing index, we should do nothing here.
* Any HOT chains that are broken with respect to the index must predate
@@ -3065,7 +3064,7 @@ index_build(Relation heapRelation,
*
* We also need not set indcheckxmin during a concurrent index build,
* because we won't set indisvalid true until all transactions that care
- * about the broken HOT chains or early pruning/vacuuming are gone.
+ * about the broken HOT chains are gone.
*
* Therefore, this code path can only be taken during non-concurrent
* CREATE INDEX. Thus the fact that heap_update will set the pg_index
@@ -3074,7 +3073,7 @@ index_build(Relation heapRelation,
* about any concurrent readers of the tuple; no other transaction can see
* it yet.
*/
- if ((indexInfo->ii_BrokenHotChain || EarlyPruningEnabled(heapRelation)) &&
+ if (indexInfo->ii_BrokenHotChain &&
!isreindex &&
!indexInfo->ii_Concurrent)
{
@@ -3759,11 +3758,6 @@ reindex_index(Oid indexId, bool skip_constraint_checks, char persistence,
* reindexing pg_index itself, we must not try to update tuples in it.
* pg_index's indexes should always have these flags in their clean state,
* so that won't happen.
- *
- * If early pruning/vacuuming is enabled for the heap relation, the
- * usability horizon must be advanced to the current transaction on every
- * build or rebuild. pg_index is OK in this regard because catalog tables
- * are not subject to early cleanup.
*/
if (!skipped_constraint)
{
@@ -3771,7 +3765,6 @@ reindex_index(Oid indexId, bool skip_constraint_checks, char persistence,
HeapTuple indexTuple;
Form_pg_index indexForm;
bool index_bad;
- bool early_pruning_enabled = EarlyPruningEnabled(heapRelation);
pg_index = table_open(IndexRelationId, RowExclusiveLock);
@@ -3785,12 +3778,11 @@ reindex_index(Oid indexId, bool skip_constraint_checks, char persistence,
!indexForm->indisready ||
!indexForm->indislive);
if (index_bad ||
- (indexForm->indcheckxmin && !indexInfo->ii_BrokenHotChain) ||
- early_pruning_enabled)
+ (indexForm->indcheckxmin && !indexInfo->ii_BrokenHotChain))
{
- if (!indexInfo->ii_BrokenHotChain && !early_pruning_enabled)
+ if (!indexInfo->ii_BrokenHotChain)
indexForm->indcheckxmin = false;
- else if (index_bad || early_pruning_enabled)
+ else if (index_bad)
indexForm->indcheckxmin = true;
indexForm->indisvalid = true;
indexForm->indisready = true;
diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c
index 69ac276687b..8bdbee68417 100644
--- a/src/backend/commands/vacuum.c
+++ b/src/backend/commands/vacuum.c
@@ -1110,25 +1110,6 @@ vacuum_get_cutoffs(Relation rel, const VacuumParams *params,
*/
cutoffs->OldestXmin = GetOldestNonRemovableTransactionId(rel);
- if (OldSnapshotThresholdActive())
- {
- TransactionId limit_xmin;
- TimestampTz limit_ts;
-
- if (TransactionIdLimitedForOldSnapshots(cutoffs->OldestXmin, rel,
- &limit_xmin, &limit_ts))
- {
- /*
- * TODO: We should only set the threshold if we are pruning on the
- * basis of the increased limits. Not as crucial here as it is
- * for opportunistic pruning (which often happens at a much higher
- * frequency), but would still be a significant improvement.
- */
- SetOldSnapshotThresholdTimestamp(limit_ts, limit_xmin);
- cutoffs->OldestXmin = limit_xmin;
- }
- }
-
Assert(TransactionIdIsNormal(cutoffs->OldestXmin));
/* Acquire OldestMxact */
diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c
index 3bd82dbfca6..da1bfefe926 100644
--- a/src/backend/storage/buffer/bufmgr.c
+++ b/src/backend/storage/buffer/bufmgr.c
@@ -5575,20 +5575,3 @@ IssuePendingWritebacks(WritebackContext *wb_context, IOContext io_context)
wb_context->nr_pending = 0;
}
-
-
-/*
- * Implement slower/larger portions of TestForOldSnapshot
- *
- * Smaller/faster portions are put inline, but the entire set of logic is too
- * big for that.
- */
-void
-TestForOldSnapshot_impl(Snapshot snapshot, Relation relation)
-{
- if (RelationAllowsEarlyPruning(relation)
- && (snapshot)->whenTaken < GetOldSnapshotThresholdTimestamp())
- ereport(ERROR,
- (errcode(ERRCODE_SNAPSHOT_TOO_OLD),
- errmsg("snapshot too old")));
-}
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 5551afffc04..a3d8eacb8dc 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -138,7 +138,6 @@ CalculateShmemSize(int *num_semaphores)
size = add_size(size, WalRcvShmemSize());
size = add_size(size, PgArchShmemSize());
size = add_size(size, ApplyLauncherShmemSize());
- size = add_size(size, SnapMgrShmemSize());
size = add_size(size, BTreeShmemSize());
size = add_size(size, SyncScanShmemSize());
size = add_size(size, AsyncShmemSize());
@@ -298,7 +297,6 @@ CreateSharedMemoryAndSemaphores(void)
/*
* Set up other modules that need some shared memory space
*/
- SnapMgrInit();
BTreeShmemInit();
SyncScanShmemInit();
AsyncShmemInit();
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index 2a3da49b8fc..aa1552e0316 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2067,34 +2067,6 @@ GetMaxSnapshotSubxidCount(void)
}
/*
- * Initialize old_snapshot_threshold specific parts of a newly build snapshot.
- */
-static void
-GetSnapshotDataInitOldSnapshot(Snapshot snapshot)
-{
- if (!OldSnapshotThresholdActive())
- {
- /*
- * If not using "snapshot too old" feature, fill related fields with
- * dummy values that don't require any locking.
- */
- snapshot->lsn = InvalidXLogRecPtr;
- snapshot->whenTaken = 0;
- }
- else
- {
- /*
- * Capture the current time and WAL stream location in case this
- * snapshot becomes old enough to need to fall back on the special
- * "old snapshot" logic.
- */
- snapshot->lsn = GetXLogInsertRecPtr();
- snapshot->whenTaken = GetSnapshotCurrentTimestamp();
- MaintainOldSnapshotTimeMapping(snapshot->whenTaken, snapshot->xmin);
- }
-}
-
-/*
* Helper function for GetSnapshotData() that checks if the bulk of the
* visibility information in the snapshot is still valid. If so, it updates
* the fields that need to change and returns true. Otherwise it returns
@@ -2147,8 +2119,8 @@ GetSnapshotDataReuse(Snapshot snapshot)
snapshot->active_count = 0;
snapshot->regd_count = 0;
snapshot->copied = false;
-
- GetSnapshotDataInitOldSnapshot(snapshot);
+ snapshot->lsn = InvalidXLogRecPtr;
+ snapshot->whenTaken = 0;
return true;
}
@@ -2529,8 +2501,8 @@ GetSnapshotData(Snapshot snapshot)
snapshot->active_count = 0;
snapshot->regd_count = 0;
snapshot->copied = false;
-
- GetSnapshotDataInitOldSnapshot(snapshot);
+ snapshot->lsn = InvalidXLogRecPtr;
+ snapshot->whenTaken = 0;
return snapshot;
}
diff --git a/src/backend/storage/lmgr/lwlocknames.txt b/src/backend/storage/lmgr/lwlocknames.txt
index 811ad947420..f72f2906cea 100644
--- a/src/backend/storage/lmgr/lwlocknames.txt
+++ b/src/backend/storage/lmgr/lwlocknames.txt
@@ -47,7 +47,7 @@ CommitTsSLRULock 38
CommitTsLock 39
ReplicationOriginLock 40
MultiXactTruncationLock 41
-OldSnapshotTimeMapLock 42
+# 42 was OldSnapshotTimeMapLock
LogicalRepWorkerLock 43
XactTruncationLock 44
# 45 was XactTruncationLock until removal of BackendRandomLock
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index 13774254d24..06a1a3df9be 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -312,7 +312,6 @@ WAIT_EVENT_DOCONLY CommitTsSLRU "Waiting to access the commit timestamp SLRU cac
WAIT_EVENT_DOCONLY CommitTs "Waiting to read or update the last value set for a transaction commit timestamp."
WAIT_EVENT_DOCONLY ReplicationOrigin "Waiting to create, drop or use a replication origin."
WAIT_EVENT_DOCONLY MultiXactTruncation "Waiting to read or truncate multixact information."
-WAIT_EVENT_DOCONLY OldSnapshotTimeMap "Waiting to read or update old snapshot control information."
WAIT_EVENT_DOCONLY LogicalRepWorker "Waiting to read or update the state of logical replication workers."
WAIT_EVENT_DOCONLY XactTruncation "Waiting to execute <function>pg_xact_status</function> or update the oldest transaction ID available to it."
WAIT_EVENT_DOCONLY WrapLimitsVacuum "Waiting to update limits on transaction id and multixact consumption."
diff --git a/src/backend/utils/errcodes.txt b/src/backend/utils/errcodes.txt
index 3d244af130a..8e97a0150f5 100644
--- a/src/backend/utils/errcodes.txt
+++ b/src/backend/utils/errcodes.txt
@@ -439,10 +439,6 @@ Section: Class 58 - System Error (errors external to PostgreSQL itself)
58P01 E ERRCODE_UNDEFINED_FILE undefined_file
58P02 E ERRCODE_DUPLICATE_FILE duplicate_file
-Section: Class 72 - Snapshot Failure
-# (class borrowed from Oracle)
-72000 E ERRCODE_SNAPSHOT_TOO_OLD snapshot_too_old
-
Section: Class F0 - Configuration File Error
# (PostgreSQL-specific error class)
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index e565a3092f6..4107d0a7355 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -3283,17 +3283,6 @@ struct config_int ConfigureNamesInt[] =
},
{
- {"old_snapshot_threshold", PGC_POSTMASTER, RESOURCES_ASYNCHRONOUS,
- gettext_noop("Time before a snapshot is too old to read pages changed after the snapshot was taken."),
- gettext_noop("A value of -1 disables this feature."),
- GUC_UNIT_MIN
- },
- &old_snapshot_threshold,
- -1, -1, MINS_PER_HOUR * HOURS_PER_DAY * 60,
- NULL, NULL, NULL
- },
-
- {
{"tcp_keepalives_idle", PGC_USERSET, CONN_AUTH_TCP,
gettext_noop("Time between issuing TCP keepalives."),
gettext_noop("A value of 0 uses the system default."),
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index c768af9a73b..6bb39d39bad 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -197,8 +197,6 @@
#max_parallel_workers = 8 # maximum number of max_worker_processes that
# can be used in parallel operations
#parallel_leader_participation = on
-#old_snapshot_threshold = -1 # 1min-60d; -1 disables; 0 is immediate
- # (change requires restart)
#------------------------------------------------------------------------------
diff --git a/src/backend/utils/time/snapmgr.c b/src/backend/utils/time/snapmgr.c
index 3a419e348fa..b20440ee21f 100644
--- a/src/backend/utils/time/snapmgr.c
+++ b/src/backend/utils/time/snapmgr.c
@@ -65,7 +65,6 @@
#include "storage/spin.h"
#include "utils/builtins.h"
#include "utils/memutils.h"
-#include "utils/old_snapshot.h"
#include "utils/rel.h"
#include "utils/resowner_private.h"
#include "utils/snapmgr.h"
@@ -74,14 +73,6 @@
/*
- * GUC parameters
- */
-int old_snapshot_threshold; /* number of minutes, -1 disables */
-
-volatile OldSnapshotControlData *oldSnapshotControl;
-
-
-/*
* CurrentSnapshot points to the only snapshot taken in transaction-snapshot
* mode, and to the latest one taken in a read-committed transaction.
* SecondarySnapshot is a snapshot that's always up-to-date as of the current
@@ -170,7 +161,6 @@ typedef struct ExportedSnapshot
static List *exportedSnapshots = NIL;
/* Prototypes for local functions */
-static TimestampTz AlignTimestampToMinuteBoundary(TimestampTz ts);
static Snapshot CopySnapshot(Snapshot snapshot);
static void FreeSnapshot(Snapshot snapshot);
static void SnapshotResetXmin(void);
@@ -194,50 +184,6 @@ typedef struct SerializedSnapshotData
XLogRecPtr lsn;
} SerializedSnapshotData;
-Size
-SnapMgrShmemSize(void)
-{
- Size size;
-
- size = offsetof(OldSnapshotControlData, xid_by_minute);
- if (old_snapshot_threshold > 0)
- size = add_size(size, mul_size(sizeof(TransactionId),
- OLD_SNAPSHOT_TIME_MAP_ENTRIES));
-
- return size;
-}
-
-/*
- * Initialize for managing old snapshot detection.
- */
-void
-SnapMgrInit(void)
-{
- bool found;
-
- /*
- * Create or attach to the OldSnapshotControlData structure.
- */
- oldSnapshotControl = (volatile OldSnapshotControlData *)
- ShmemInitStruct("OldSnapshotControlData",
- SnapMgrShmemSize(), &found);
-
- if (!found)
- {
- SpinLockInit(&oldSnapshotControl->mutex_current);
- oldSnapshotControl->current_timestamp = 0;
- SpinLockInit(&oldSnapshotControl->mutex_latest_xmin);
- oldSnapshotControl->latest_xmin = InvalidTransactionId;
- oldSnapshotControl->next_map_update = 0;
- SpinLockInit(&oldSnapshotControl->mutex_threshold);
- oldSnapshotControl->threshold_timestamp = 0;
- oldSnapshotControl->threshold_xid = InvalidTransactionId;
- oldSnapshotControl->head_offset = 0;
- oldSnapshotControl->head_timestamp = 0;
- oldSnapshotControl->count_used = 0;
- }
-}
-
/*
* GetTransactionSnapshot
* Get the appropriate snapshot for a new query in a transaction.
@@ -1657,420 +1603,6 @@ HaveRegisteredOrActiveSnapshot(void)
/*
- * Return a timestamp that is exactly on a minute boundary.
- *
- * If the argument is already aligned, return that value, otherwise move to
- * the next minute boundary following the given time.
- */
-static TimestampTz
-AlignTimestampToMinuteBoundary(TimestampTz ts)
-{
- TimestampTz retval = ts + (USECS_PER_MINUTE - 1);
-
- return retval - (retval % USECS_PER_MINUTE);
-}
-
-/*
- * Get current timestamp for snapshots
- *
- * This is basically GetCurrentTimestamp(), but with a guarantee that
- * the result never moves backward.
- */
-TimestampTz
-GetSnapshotCurrentTimestamp(void)
-{
- TimestampTz now = GetCurrentTimestamp();
-
- /*
- * Don't let time move backward; if it hasn't advanced, use the old value.
- */
- SpinLockAcquire(&oldSnapshotControl->mutex_current);
- if (now <= oldSnapshotControl->current_timestamp)
- now = oldSnapshotControl->current_timestamp;
- else
- oldSnapshotControl->current_timestamp = now;
- SpinLockRelease(&oldSnapshotControl->mutex_current);
-
- return now;
-}
-
-/*
- * Get timestamp through which vacuum may have processed based on last stored
- * value for threshold_timestamp.
- *
- * XXX: So far, we never trust that a 64-bit value can be read atomically; if
- * that ever changes, we could get rid of the spinlock here.
- */
-TimestampTz
-GetOldSnapshotThresholdTimestamp(void)
-{
- TimestampTz threshold_timestamp;
-
- SpinLockAcquire(&oldSnapshotControl->mutex_threshold);
- threshold_timestamp = oldSnapshotControl->threshold_timestamp;
- SpinLockRelease(&oldSnapshotControl->mutex_threshold);
-
- return threshold_timestamp;
-}
-
-void
-SetOldSnapshotThresholdTimestamp(TimestampTz ts, TransactionId xlimit)
-{
- SpinLockAcquire(&oldSnapshotControl->mutex_threshold);
- Assert(oldSnapshotControl->threshold_timestamp <= ts);
- Assert(TransactionIdPrecedesOrEquals(oldSnapshotControl->threshold_xid, xlimit));
- oldSnapshotControl->threshold_timestamp = ts;
- oldSnapshotControl->threshold_xid = xlimit;
- SpinLockRelease(&oldSnapshotControl->mutex_threshold);
-}
-
-/*
- * XXX: Magic to keep old_snapshot_threshold tests appear "working". They
- * currently are broken, and discussion of what to do about them is
- * ongoing. See
- * https://www.postgresql.org/message-id/20200403001235.e6jfdll3gh2ygbuc%40alap3.anarazel.de
- */
-void
-SnapshotTooOldMagicForTest(void)
-{
- TimestampTz ts = GetSnapshotCurrentTimestamp();
-
- Assert(old_snapshot_threshold == 0);
-
- ts -= 5 * USECS_PER_SEC;
-
- SpinLockAcquire(&oldSnapshotControl->mutex_threshold);
- oldSnapshotControl->threshold_timestamp = ts;
- SpinLockRelease(&oldSnapshotControl->mutex_threshold);
-}
-
-/*
- * If there is a valid mapping for the timestamp, set *xlimitp to
- * that. Returns whether there is such a mapping.
- */
-static bool
-GetOldSnapshotFromTimeMapping(TimestampTz ts, TransactionId *xlimitp)
-{
- bool in_mapping = false;
-
- Assert(ts == AlignTimestampToMinuteBoundary(ts));
-
- LWLockAcquire(OldSnapshotTimeMapLock, LW_SHARED);
-
- if (oldSnapshotControl->count_used > 0
- && ts >= oldSnapshotControl->head_timestamp)
- {
- int offset;
-
- offset = ((ts - oldSnapshotControl->head_timestamp)
- / USECS_PER_MINUTE);
- if (offset > oldSnapshotControl->count_used - 1)
- offset = oldSnapshotControl->count_used - 1;
- offset = (oldSnapshotControl->head_offset + offset)
- % OLD_SNAPSHOT_TIME_MAP_ENTRIES;
-
- *xlimitp = oldSnapshotControl->xid_by_minute[offset];
-
- in_mapping = true;
- }
-
- LWLockRelease(OldSnapshotTimeMapLock);
-
- return in_mapping;
-}
-
-/*
- * TransactionIdLimitedForOldSnapshots
- *
- * Apply old snapshot limit. This is intended to be called for page pruning
- * and table vacuuming, to allow old_snapshot_threshold to override the normal
- * global xmin value. Actual testing for snapshot too old will be based on
- * whether a snapshot timestamp is prior to the threshold timestamp set in
- * this function.
- *
- * If the limited horizon allows a cleanup action that otherwise would not be
- * possible, SetOldSnapshotThresholdTimestamp(*limit_ts, *limit_xid) needs to
- * be called before that cleanup action.
- */
-bool
-TransactionIdLimitedForOldSnapshots(TransactionId recentXmin,
- Relation relation,
- TransactionId *limit_xid,
- TimestampTz *limit_ts)
-{
- TimestampTz ts;
- TransactionId xlimit = recentXmin;
- TransactionId latest_xmin;
- TimestampTz next_map_update_ts;
- TransactionId threshold_timestamp;
- TransactionId threshold_xid;
-
- Assert(TransactionIdIsNormal(recentXmin));
- Assert(OldSnapshotThresholdActive());
- Assert(limit_ts != NULL && limit_xid != NULL);
-
- /*
- * TestForOldSnapshot() assumes early pruning advances the page LSN, so we
- * can't prune early when skipping WAL.
- */
- if (!RelationAllowsEarlyPruning(relation) || !RelationNeedsWAL(relation))
- return false;
-
- ts = GetSnapshotCurrentTimestamp();
-
- SpinLockAcquire(&oldSnapshotControl->mutex_latest_xmin);
- latest_xmin = oldSnapshotControl->latest_xmin;
- next_map_update_ts = oldSnapshotControl->next_map_update;
- SpinLockRelease(&oldSnapshotControl->mutex_latest_xmin);
-
- /*
- * Zero threshold always overrides to latest xmin, if valid. Without some
- * heuristic it will find its own snapshot too old on, for example, a
- * simple UPDATE -- which would make it useless for most testing, but
- * there is no principled way to ensure that it doesn't fail in this way.
- * Use a five-second delay to try to get useful testing behavior, but this
- * may need adjustment.
- */
- if (old_snapshot_threshold == 0)
- {
- if (TransactionIdPrecedes(latest_xmin, MyProc->xmin)
- && TransactionIdFollows(latest_xmin, xlimit))
- xlimit = latest_xmin;
-
- ts -= 5 * USECS_PER_SEC;
- }
- else
- {
- ts = AlignTimestampToMinuteBoundary(ts)
- - (old_snapshot_threshold * USECS_PER_MINUTE);
-
- /* Check for fast exit without LW locking. */
- SpinLockAcquire(&oldSnapshotControl->mutex_threshold);
- threshold_timestamp = oldSnapshotControl->threshold_timestamp;
- threshold_xid = oldSnapshotControl->threshold_xid;
- SpinLockRelease(&oldSnapshotControl->mutex_threshold);
-
- if (ts == threshold_timestamp)
- {
- /*
- * Current timestamp is in same bucket as the last limit that was
- * applied. Reuse.
- */
- xlimit = threshold_xid;
- }
- else if (ts == next_map_update_ts)
- {
- /*
- * FIXME: This branch is super iffy - but that should probably
- * fixed separately.
- */
- xlimit = latest_xmin;
- }
- else if (GetOldSnapshotFromTimeMapping(ts, &xlimit))
- {
- }
-
- /*
- * Failsafe protection against vacuuming work of active transaction.
- *
- * This is not an assertion because we avoid the spinlock for
- * performance, leaving open the possibility that xlimit could advance
- * and be more current; but it seems prudent to apply this limit. It
- * might make pruning a tiny bit less aggressive than it could be, but
- * protects against data loss bugs.
- */
- if (TransactionIdIsNormal(latest_xmin)
- && TransactionIdPrecedes(latest_xmin, xlimit))
- xlimit = latest_xmin;
- }
-
- if (TransactionIdIsValid(xlimit) &&
- TransactionIdFollowsOrEquals(xlimit, recentXmin))
- {
- *limit_ts = ts;
- *limit_xid = xlimit;
-
- return true;
- }
-
- return false;
-}
-
-/*
- * Take care of the circular buffer that maps time to xid.
- */
-void
-MaintainOldSnapshotTimeMapping(TimestampTz whenTaken, TransactionId xmin)
-{
- TimestampTz ts;
- TransactionId latest_xmin;
- TimestampTz update_ts;
- bool map_update_required = false;
-
- /* Never call this function when old snapshot checking is disabled. */
- Assert(old_snapshot_threshold >= 0);
-
- ts = AlignTimestampToMinuteBoundary(whenTaken);
-
- /*
- * Keep track of the latest xmin seen by any process. Update mapping with
- * a new value when we have crossed a bucket boundary.
- */
- SpinLockAcquire(&oldSnapshotControl->mutex_latest_xmin);
- latest_xmin = oldSnapshotControl->latest_xmin;
- update_ts = oldSnapshotControl->next_map_update;
- if (ts > update_ts)
- {
- oldSnapshotControl->next_map_update = ts;
- map_update_required = true;
- }
- if (TransactionIdFollows(xmin, latest_xmin))
- oldSnapshotControl->latest_xmin = xmin;
- SpinLockRelease(&oldSnapshotControl->mutex_latest_xmin);
-
- /* We only needed to update the most recent xmin value. */
- if (!map_update_required)
- return;
-
- /* No further tracking needed for 0 (used for testing). */
- if (old_snapshot_threshold == 0)
- return;
-
- /*
- * We don't want to do something stupid with unusual values, but we don't
- * want to litter the log with warnings or break otherwise normal
- * processing for this feature; so if something seems unreasonable, just
- * log at DEBUG level and return without doing anything.
- */
- if (whenTaken < 0)
- {
- elog(DEBUG1,
- "MaintainOldSnapshotTimeMapping called with negative whenTaken = %ld",
- (long) whenTaken);
- return;
- }
- if (!TransactionIdIsNormal(xmin))
- {
- elog(DEBUG1,
- "MaintainOldSnapshotTimeMapping called with xmin = %lu",
- (unsigned long) xmin);
- return;
- }
-
- LWLockAcquire(OldSnapshotTimeMapLock, LW_EXCLUSIVE);
-
- Assert(oldSnapshotControl->head_offset >= 0);
- Assert(oldSnapshotControl->head_offset < OLD_SNAPSHOT_TIME_MAP_ENTRIES);
- Assert((oldSnapshotControl->head_timestamp % USECS_PER_MINUTE) == 0);
- Assert(oldSnapshotControl->count_used >= 0);
- Assert(oldSnapshotControl->count_used <= OLD_SNAPSHOT_TIME_MAP_ENTRIES);
-
- if (oldSnapshotControl->count_used == 0)
- {
- /* set up first entry for empty mapping */
- oldSnapshotControl->head_offset = 0;
- oldSnapshotControl->head_timestamp = ts;
- oldSnapshotControl->count_used = 1;
- oldSnapshotControl->xid_by_minute[0] = xmin;
- }
- else if (ts < oldSnapshotControl->head_timestamp)
- {
- /* old ts; log it at DEBUG */
- LWLockRelease(OldSnapshotTimeMapLock);
- elog(DEBUG1,
- "MaintainOldSnapshotTimeMapping called with old whenTaken = %ld",
- (long) whenTaken);
- return;
- }
- else if (ts <= (oldSnapshotControl->head_timestamp +
- ((oldSnapshotControl->count_used - 1)
- * USECS_PER_MINUTE)))
- {
- /* existing mapping; advance xid if possible */
- int bucket = (oldSnapshotControl->head_offset
- + ((ts - oldSnapshotControl->head_timestamp)
- / USECS_PER_MINUTE))
- % OLD_SNAPSHOT_TIME_MAP_ENTRIES;
-
- if (TransactionIdPrecedes(oldSnapshotControl->xid_by_minute[bucket], xmin))
- oldSnapshotControl->xid_by_minute[bucket] = xmin;
- }
- else
- {
- /* We need a new bucket, but it might not be the very next one. */
- int distance_to_new_tail;
- int distance_to_current_tail;
- int advance;
-
- /*
- * Our goal is for the new "tail" of the mapping, that is, the entry
- * which is newest and thus furthest from the "head" entry, to
- * correspond to "ts". Since there's one entry per minute, the
- * distance between the current head and the new tail is just the
- * number of minutes of difference between ts and the current
- * head_timestamp.
- *
- * The distance from the current head to the current tail is one less
- * than the number of entries in the mapping, because the entry at the
- * head_offset is for 0 minutes after head_timestamp.
- *
- * The difference between these two values is the number of minutes by
- * which we need to advance the mapping, either adding new entries or
- * rotating old ones out.
- */
- distance_to_new_tail =
- (ts - oldSnapshotControl->head_timestamp) / USECS_PER_MINUTE;
- distance_to_current_tail =
- oldSnapshotControl->count_used - 1;
- advance = distance_to_new_tail - distance_to_current_tail;
- Assert(advance > 0);
-
- if (advance >= OLD_SNAPSHOT_TIME_MAP_ENTRIES)
- {
- /* Advance is so far that all old data is junk; start over. */
- oldSnapshotControl->head_offset = 0;
- oldSnapshotControl->count_used = 1;
- oldSnapshotControl->xid_by_minute[0] = xmin;
- oldSnapshotControl->head_timestamp = ts;
- }
- else
- {
- /* Store the new value in one or more buckets. */
- int i;
-
- for (i = 0; i < advance; i++)
- {
- if (oldSnapshotControl->count_used == OLD_SNAPSHOT_TIME_MAP_ENTRIES)
- {
- /* Map full and new value replaces old head. */
- int old_head = oldSnapshotControl->head_offset;
-
- if (old_head == (OLD_SNAPSHOT_TIME_MAP_ENTRIES - 1))
- oldSnapshotControl->head_offset = 0;
- else
- oldSnapshotControl->head_offset = old_head + 1;
- oldSnapshotControl->xid_by_minute[old_head] = xmin;
- oldSnapshotControl->head_timestamp += USECS_PER_MINUTE;
- }
- else
- {
- /* Extend map to unused entry. */
- int new_tail = (oldSnapshotControl->head_offset
- + oldSnapshotControl->count_used)
- % OLD_SNAPSHOT_TIME_MAP_ENTRIES;
-
- oldSnapshotControl->count_used++;
- oldSnapshotControl->xid_by_minute[new_tail] = xmin;
- }
- }
- }
- }
-
- LWLockRelease(OldSnapshotTimeMapLock);
-}
-
-
-/*
* Setup a snapshot that replaces normal catalog snapshots that allows catalog
* access to behave just like it did at a certain point in the past.
*