database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-07 00:36:50 +03:00
Code Activity

Revert "Skip WAL for new relfilenodes, under wal_level=minimal."

Browse Source 
This reverts commit cb2fd7eac2.  Per
numerous buildfarm members, it was incompatible with parallel query, and
a test case assumed LP64.  Back-patch to 9.5 (all supported versions).

Discussion: https://postgr.es/m/20200321224920.GB1763544@rfd.leadboat.com
This commit is contained in:
Noah Misch
2020-03-22 09:24:09 -07:00
parent e4b0a02ef8
commit 63631ee64f
51 changed files with 331 additions and 1446 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
src/backend/access/gist/gistutil.c
View File

@ -1019,44 +1019,23 @@ gistproperty(Oid index_oid, int attno,
}
/*
* Some indexes are not WAL-logged, but we need LSNs to detect concurrent page
* splits anyway. This function provides a fake sequence of LSNs for that
* purpose.
* Temporary and unlogged GiST indexes are not WAL-logged, but we need LSNs
* to detect concurrent page splits anyway. This function provides a fake
* sequence of LSNs for that purpose.
*/
XLogRecPtr
gistGetFakeLSN(Relation rel)
{
static XLogRecPtr counter = FirstNormalUnloggedLSN;
if (rel->rd_rel->relpersistence == RELPERSISTENCE_TEMP)
{
/*
* Temporary relations are only accessible in our session, so a simple
* backend-local counter will do.
*/
static XLogRecPtr counter = FirstNormalUnloggedLSN;
return counter++;
}
else if (rel->rd_rel->relpersistence == RELPERSISTENCE_PERMANENT)
{
/*
* WAL-logging on this relation will start after commit, so its LSNs
* must be distinct numbers smaller than the LSN at the next commit.
* Emit a dummy WAL record if insert-LSN hasn't advanced after the
* last call.
*/
static XLogRecPtr lastlsn = InvalidXLogRecPtr;
XLogRecPtr currlsn = GetXLogInsertRecPtr();
/* Shouldn't be called for WAL-logging relations */
Assert(!RelationNeedsWAL(rel));
/* No need for an actual record if we already have a distinct LSN */
if (!XLogRecPtrIsInvalid(lastlsn) && lastlsn == currlsn)
currlsn = gistXLogAssignLSN();
lastlsn = currlsn;
return currlsn;
}
else
{
/*

21
src/backend/access/gist/gistxlog.c
View File

@ -449,9 +449,6 @@ gist_redo(XLogReaderState *record)
case XLOG_GIST_PAGE_DELETE:
gistRedoPageDelete(record);
break;
case XLOG_GIST_ASSIGN_LSN:
/* nop. See gistGetFakeLSN(). */
break;
default:
elog(PANIC, "gist_redo: unknown op code %u", info);
}
@ -595,24 +592,6 @@ gistXLogPageDelete(Buffer buffer, FullTransactionId xid,
return recptr;
}
/*
* Write an empty XLOG record to assign a distinct LSN.
*/
XLogRecPtr
gistXLogAssignLSN(void)
{
int dummy = 0;
/*
* Records other than SWITCH_WAL must have content. We use an integer 0 to
* follow the restriction.
*/
XLogBeginInsert();
XLogSetRecordFlags(XLOG_MARK_UNIMPORTANT);
XLogRegisterData((char *) &dummy, sizeof(dummy));
return XLogInsert(RM_GIST_ID, XLOG_GIST_ASSIGN_LSN);
}
/*
* Write XLOG record about reuse of a deleted page.
*/

22
src/backend/access/heap/heapam.c
View File

@ -21,6 +21,7 @@
* heap_multi_insert - insert multiple tuples into a relation
* heap_delete - delete a tuple from a relation
* heap_update - replace a tuple in a relation with another tuple
* heap_sync - sync heap, for when no WAL has been written
*
* NOTES
* This file contains the heap_ routines which implement
@ -1935,7 +1936,7 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid,
MarkBufferDirty(buffer);
/* XLOG stuff */
if (RelationNeedsWAL(relation))
if (!(options & HEAP_INSERT_SKIP_WAL) && RelationNeedsWAL(relation))
{
xl_heap_insert xlrec;
xl_heap_header xlhdr;
@ -2118,7 +2119,7 @@ heap_multi_insert(Relation relation, TupleTableSlot **slots, int ntuples,
/* currently not needed (thus unsupported) for heap_multi_insert() */
AssertArg(!(options & HEAP_INSERT_NO_LOGICAL));
needwal = RelationNeedsWAL(relation);
needwal = !(options & HEAP_INSERT_SKIP_WAL) && RelationNeedsWAL(relation);
saveFreeSpace = RelationGetTargetPageFreeSpace(relation,
HEAP_DEFAULT_FILLFACTOR);
@ -8920,13 +8921,18 @@ heap2_redo(XLogReaderState *record)
}
/*
* heap_sync - for binary compatibility
* heap_sync - sync a heap, for use when no WAL has been written
*
* A newer PostgreSQL version removes this function. It exists here just in
* case an extension calls it. See "Skipping WAL for New RelFileNode" in
* src/backend/access/transam/README for the system that superseded it,
* allowing removal of most calls. Cases like RelationCopyStorage() should
* call smgrimmedsync() directly.
* This forces the heap contents (including TOAST heap if any) down to disk.
* If we skipped using WAL, and WAL is otherwise needed, we must force the
* relation down to disk before it's safe to commit the transaction. This
* requires writing out any dirty buffers and then doing a forced fsync.
*
* Indexes are not touched. (Currently, index operations associated with
* the commands that use this are WAL-logged and so do not need fsync.
* That behavior might change someday, but in any case it's likely that
* any fsync decisions required would be per-index and hence not appropriate
* to be done here.)
*/
void
heap_sync(Relation rel)

22
src/backend/access/heap/heapam_handler.c
View File

@ -559,6 +559,17 @@ tuple_lock_retry:
return result;
}
static void
heapam_finish_bulk_insert(Relation relation, int options)
{
/*
* If we skipped writing WAL, then we need to sync the heap (but not
* indexes since those use WAL anyway / don't go through tableam)
*/
if (options & HEAP_INSERT_SKIP_WAL)
heap_sync(relation);
}
/* ------------------------------------------------------------------------
* DDL related callbacks for heap AM.
@ -691,6 +702,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
IndexScanDesc indexScan;
TableScanDesc tableScan;
HeapScanDesc heapScan;
bool use_wal;
bool is_system_catalog;
Tuplesortstate *tuplesort;
TupleDesc oldTupDesc = RelationGetDescr(OldHeap);
@ -705,9 +717,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
is_system_catalog = IsSystemRelation(OldHeap);
/*
* Valid smgr_targblock implies something already wrote to the relation.
* This may be harmless, but this function hasn't planned for it.
* We need to log the copied data in WAL iff WAL archiving/streaming is
* enabled AND it's a WAL-logged rel.
*/
use_wal = XLogIsNeeded() && RelationNeedsWAL(NewHeap);
/* use_wal off requires smgr_targblock be initially invalid */
Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
/* Preallocate values/isnull arrays */
@ -717,7 +732,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
/* Initialize the rewrite operation */
rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, *xid_cutoff,
*multi_cutoff);
*multi_cutoff, use_wal);
/* Set up sorting if wanted */
@ -2611,6 +2626,7 @@ static const TableAmRoutine heapam_methods = {
.tuple_delete = heapam_tuple_delete,
.tuple_update = heapam_tuple_update,
.tuple_lock = heapam_tuple_lock,
.finish_bulk_insert = heapam_finish_bulk_insert,
.tuple_fetch_row_version = heapam_fetch_row_version,
.tuple_get_latest_tid = heap_get_latest_tid,

21
src/backend/access/heap/rewriteheap.c
View File

@ -144,6 +144,7 @@ typedef struct RewriteStateData
Page rs_buffer; /* page currently being built */
BlockNumber rs_blockno; /* block where page will go */
bool rs_buffer_valid; /* T if any tuples in buffer */
bool rs_use_wal; /* must we WAL-log inserts? */
bool rs_logical_rewrite; /* do we need to do logical rewriting */
TransactionId rs_oldest_xmin; /* oldest xmin used by caller to determine
* tuple visibility */
@ -237,13 +238,15 @@ static void logical_end_heap_rewrite(RewriteState state);
* oldest_xmin xid used by the caller to determine which tuples are dead
* freeze_xid xid before which tuples will be frozen
* min_multi multixact before which multis will be removed
* use_wal should the inserts to the new heap be WAL-logged?
*
* Returns an opaque RewriteState, allocated in current memory context,
* to be used in subsequent calls to the other functions.
*/
RewriteState
begin_heap_rewrite(Relation old_heap, Relation new_heap, TransactionId oldest_xmin,
TransactionId freeze_xid, MultiXactId cutoff_multi)
TransactionId freeze_xid, MultiXactId cutoff_multi,
bool use_wal)
{
RewriteState state;
MemoryContext rw_cxt;
@ -268,6 +271,7 @@ begin_heap_rewrite(Relation old_heap, Relation new_heap, TransactionId oldest_xm
/* new_heap needn't be empty, just locked */
state->rs_blockno = RelationGetNumberOfBlocks(new_heap);
state->rs_buffer_valid = false;
state->rs_use_wal = use_wal;
state->rs_oldest_xmin = oldest_xmin;
state->rs_freeze_xid = freeze_xid;
state->rs_cutoff_multi = cutoff_multi;
@ -326,7 +330,7 @@ end_heap_rewrite(RewriteState state)
/* Write the last page, if any */
if (state->rs_buffer_valid)
{
if (RelationNeedsWAL(state->rs_new_rel))
if (state->rs_use_wal)
log_newpage(&state->rs_new_rel->rd_node,
MAIN_FORKNUM,
state->rs_blockno,
@ -341,14 +345,18 @@ end_heap_rewrite(RewriteState state)
}
/*
* When we WAL-logged rel pages, we must nonetheless fsync them. The
* If the rel is WAL-logged, must fsync before commit. We use heap_sync
* to ensure that the toast table gets fsync'd too.
*
* It's obvious that we must do this when not WAL-logging. It's less
* obvious that we have to do it even if we did WAL-log the pages. The
* reason is the same as in storage.c's RelationCopyStorage(): we're
* writing data that's not in shared buffers, and so a CHECKPOINT
* occurring during the rewriteheap operation won't have fsync'd data we
* wrote before the checkpoint.
*/
if (RelationNeedsWAL(state->rs_new_rel))
smgrimmedsync(state->rs_new_rel->rd_smgr, MAIN_FORKNUM);
heap_sync(state->rs_new_rel);
logical_end_heap_rewrite(state);
@ -646,6 +654,9 @@ raw_heap_insert(RewriteState state, HeapTuple tup)
{
int options = HEAP_INSERT_SKIP_FSM;
if (!state->rs_use_wal)
options |= HEAP_INSERT_SKIP_WAL;
/*
* While rewriting the heap for VACUUM FULL / CLUSTER, make sure data
* for the TOAST table are not logically decoded. The main heap is
@ -684,7 +695,7 @@ raw_heap_insert(RewriteState state, HeapTuple tup)
/* Doesn't fit, so write out the existing page */
/* XLOG stuff */
if (RelationNeedsWAL(state->rs_new_rel))
if (state->rs_use_wal)
log_newpage(&state->rs_new_rel->rd_node,
MAIN_FORKNUM,
state->rs_blockno,

41
src/backend/access/nbtree/nbtsort.c
View File

@ -31,6 +31,18 @@
* them. They will need to be re-read into shared buffers on first use after
* the build finishes.
*
* Since the index will never be used unless it is completely built,
* from a crash-recovery point of view there is no need to WAL-log the
* steps of the build. After completing the index build, we can just sync
* the whole file to disk using smgrimmedsync() before exiting this module.
* This can be seen to be sufficient for crash recovery by considering that
* it's effectively equivalent to what would happen if a CHECKPOINT occurred
* just after the index build. However, it is clearly not sufficient if the
* DBA is using the WAL log for PITR or replication purposes, since another
* machine would not be able to reconstruct the index from WAL. Therefore,
* we log the completed index pages to WAL if and only if WAL archiving is
* active.
*
* This code isn't concerned about the FSM at all. The caller is responsible
* for initializing that.
*
@ -560,7 +572,12 @@ _bt_leafbuild(BTSpool *btspool, BTSpool *btspool2)
wstate.heap = btspool->heap;
wstate.index = btspool->index;
wstate.inskey = _bt_mkscankey(wstate.index, NULL);
wstate.btws_use_wal = RelationNeedsWAL(wstate.index);
/*
* We need to log index creation in WAL iff WAL archiving/streaming is
* enabled UNLESS the index isn't WAL-logged anyway.
*/
wstate.btws_use_wal = XLogIsNeeded() && RelationNeedsWAL(wstate.index);
/* reserve the metapage */
wstate.btws_pages_alloced = BTREE_METAPAGE + 1;
@ -1269,15 +1286,21 @@ _bt_load(BTWriteState *wstate, BTSpool *btspool, BTSpool *btspool2)
_bt_uppershutdown(wstate, state);
/*
* When we WAL-logged index pages, we must nonetheless fsync index files.
* Since we're building outside shared buffers, a CHECKPOINT occurring
* during the build has no way to flush the previously written data to
* disk (indeed it won't know the index even exists). A crash later on
* would replay WAL from the checkpoint, therefore it wouldn't replay our
* earlier WAL entries. If we do not fsync those pages here, they might
* still not be on disk when the crash occurs.
* If the index is WAL-logged, we must fsync it down to disk before it's
* safe to commit the transaction. (For a non-WAL-logged index we don't
* care since the index will be uninteresting after a crash anyway.)
*
* It's obvious that we must do this when not WAL-logging the build. It's
* less obvious that we have to do it even if we did WAL-log the index
* pages. The reason is that since we're building outside shared buffers,
* a CHECKPOINT occurring during the build has no way to flush the
* previously written data to disk (indeed it won't know the index even
* exists). A crash later on would replay WAL from the checkpoint,
* therefore it wouldn't replay our earlier WAL entries. If we do not
* fsync those pages here, they might still not be on disk when the crash
* occurs.
*/
if (wstate->btws_use_wal)
if (RelationNeedsWAL(wstate->index))
{
RelationOpenSmgr(wstate->index);
smgrimmedsync(wstate->index->rd_smgr, MAIN_FORKNUM);

6
src/backend/access/rmgrdesc/gistdesc.c
View File

@ -80,9 +80,6 @@ gist_desc(StringInfo buf, XLogReaderState *record)
case XLOG_GIST_PAGE_DELETE:
out_gistxlogPageDelete(buf, (gistxlogPageDelete *) rec);
break;
case XLOG_GIST_ASSIGN_LSN:
/* No details to write out */
break;
}
}
@ -108,9 +105,6 @@ gist_identify(uint8 info)
case XLOG_GIST_PAGE_DELETE:
id = "PAGE_DELETE";
break;
case XLOG_GIST_ASSIGN_LSN:
id = "ASSIGN_LSN";
break;
}
return id;

45
src/backend/access/transam/README
View File

@ -717,38 +717,6 @@ then restart recovery. This is part of the reason for not writing a WAL
entry until we've successfully done the original action.
Skipping WAL for New RelFileNode
--------------------------------
Under wal_level=minimal, if a change modifies a relfilenode that ROLLBACK
would unlink, in-tree access methods write no WAL for that change. Code that
writes WAL without calling RelationNeedsWAL() must check for this case. This
skipping is mandatory. If a WAL-writing change preceded a WAL-skipping change
for the same block, REDO could overwrite the WAL-skipping change. If a
WAL-writing change followed a WAL-skipping change for the same block, a
related problem would arise. When a WAL record contains no full-page image,
REDO expects the page to match its contents from just before record insertion.
A WAL-skipping change may not reach disk at all, violating REDO's expectation
under full_page_writes=off. For any access method, CommitTransaction() writes
and fsyncs affected blocks before recording the commit.
Prefer to do the same in future access methods. However, two other approaches
can work. First, an access method can irreversibly transition a given fork
from WAL-skipping to WAL-writing by calling FlushRelationBuffers() and
smgrimmedsync(). Second, an access method can opt to write WAL
unconditionally for permanent relations. Under these approaches, the access
method callbacks must not call functions that react to RelationNeedsWAL().
This applies only to WAL records whose replay would modify bytes stored in the
new relfilenode. It does not apply to other records about the relfilenode,
such as XLOG_SMGR_CREATE. Because it operates at the level of individual
relfilenodes, RelationNeedsWAL() can differ for tightly-coupled relations.
Consider "CREATE TABLE t (); BEGIN; ALTER TABLE t ADD c text; ..." in which
ALTER TABLE adds a TOAST relation. The TOAST relation will skip WAL, while
the table owning it will not. ALTER TABLE SET TABLESPACE will cause a table
to skip WAL, but that won't affect its indexes.
Asynchronous Commit
-------------------
@ -852,12 +820,13 @@ Changes to a temp table are not WAL-logged, hence could reach disk in
advance of T1's commit, but we don't care since temp table contents don't
survive crashes anyway.
Database writes that skip WAL for new relfilenodes are also safe. In these
cases it's entirely possible for the data to reach disk before T1's commit,
because T1 will fsync it down to disk without any sort of interlock. However,
all these paths are designed to write data that no other transaction can see
until after T1 commits. The situation is thus not different from ordinary
WAL-logged updates.
Database writes made via any of the paths we have introduced to avoid WAL
overhead for bulk updates are also safe. In these cases it's entirely
possible for the data to reach disk before T1's commit, because T1 will
fsync it down to disk without any sort of interlock, as soon as it finishes
the bulk update. However, all these paths are designed to write data that
no other transaction can see until after T1 commits. The situation is thus
not different from ordinary WAL-logged updates.
Transaction Emulation during Recovery
-------------------------------------

15
src/backend/access/transam/xact.c
View File

@ -2107,13 +2107,6 @@ CommitTransaction(void)
*/
PreCommit_on_commit_actions();
/*
* Synchronize files that are created and not WAL-logged during this
* transaction. This must happen before AtEOXact_RelationMap(), so that we
* don't see committed-but-broken files after a crash.
*/
smgrDoPendingSyncs(true);
/* close large objects before lower-level cleanup */
AtEOXact_LargeObject(true);
@ -2347,13 +2340,6 @@ PrepareTransaction(void)
*/
PreCommit_on_commit_actions();
/*
* Synchronize files that are created and not WAL-logged during this
* transaction. This must happen before EndPrepare(), so that we don't see
* committed-but-broken files after a crash and COMMIT PREPARED.
*/
smgrDoPendingSyncs(true);
/* close large objects before lower-level cleanup */
AtEOXact_LargeObject(true);
@ -2672,7 +2658,6 @@ AbortTransaction(void)
*/
AfterTriggerEndXact(false); /* 'false' means it's abort */
AtAbort_Portals();
smgrDoPendingSyncs(false);
AtEOXact_LargeObject(false);
AtAbort_Notify();
AtEOXact_RelationMap(false, is_parallel_worker);

18
src/backend/access/transam/xlogutils.c
View File

@ -544,8 +544,6 @@ typedef FakeRelCacheEntryData *FakeRelCacheEntry;
* fields related to physical storage, like rd_rel, are initialized, so the
* fake entry is only usable in low-level operations like ReadBuffer().
*
* This is also used for syncing WAL-skipped files.
*
* Caller must free the returned entry with FreeFakeRelcacheEntry().
*/
Relation
@ -554,20 +552,18 @@ CreateFakeRelcacheEntry(RelFileNode rnode)
FakeRelCacheEntry fakeentry;
Relation rel;
Assert(InRecovery);
/* Allocate the Relation struct and all related space in one block. */
fakeentry = palloc0(sizeof(FakeRelCacheEntryData));
rel = (Relation) fakeentry;
rel->rd_rel = &fakeentry->pgc;
rel->rd_node = rnode;
/*
* We will never be working with temp rels during recovery or while
* syncing WAL-skipped files.
*/
/* We will never be working with temp rels during recovery */
rel->rd_backend = InvalidBackendId;
/* It must be a permanent table here */
/* It must be a permanent table if we're in recovery. */
rel->rd_rel->relpersistence = RELPERSISTENCE_PERMANENT;
/* We don't know the name of the relation; use relfilenode instead */
@ -576,9 +572,9 @@ CreateFakeRelcacheEntry(RelFileNode rnode)
/*
* We set up the lockRelId in case anything tries to lock the dummy
* relation. Note that this is fairly bogus since relNode may be
* different from the relation's OID. It shouldn't really matter though.
* In recovery, we are running by ourselves and can't have any lock
* conflicts. While syncing, we already hold AccessExclusiveLock.
* different from the relation's OID. It shouldn't really matter though,
* since we are presumably running by ourselves and can't have any lock
* conflicts ...
*/
rel->rd_lockInfo.lockRelId.dbId = rnode.dbNode;
rel->rd_lockInfo.lockRelId.relId = rnode.relNode;

4
src/backend/bootstrap/bootparse.y
View File

@ -306,8 +306,6 @@ Boot_DeclareIndexStmt:
stmt->idxcomment = NULL;
stmt->indexOid = InvalidOid;
stmt->oldNode = InvalidOid;
stmt->oldCreateSubid = InvalidSubTransactionId;
stmt->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
stmt->unique = false;
stmt->primary = false;
stmt->isconstraint = false;
@ -358,8 +356,6 @@ Boot_DeclareUniqueIndexStmt:
stmt->idxcomment = NULL;
stmt->indexOid = InvalidOid;
stmt->oldNode = InvalidOid;
stmt->oldCreateSubid = InvalidSubTransactionId;
stmt->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
stmt->unique = true;
stmt->primary = false;
stmt->isconstraint = false;

246
src/backend/catalog/storage.c
View File

@ -30,13 +30,9 @@
#include "catalog/storage_xlog.h"
#include "storage/freespace.h"
#include "storage/smgr.h"
#include "utils/hsearch.h"
#include "utils/memutils.h"
#include "utils/rel.h"
/* GUC variables */
int wal_skip_threshold = 2048; /* in kilobytes */
/*
* We keep a list of all relations (represented as RelFileNode values)
* that have been created or deleted in the current transaction. When
@ -66,14 +62,7 @@ typedef struct PendingRelDelete
struct PendingRelDelete *next; /* linked-list link */
} PendingRelDelete;
typedef struct pendingSync
{
RelFileNode rnode;
bool is_truncated; /* Has the file experienced truncation? */
} pendingSync;
static PendingRelDelete *pendingDeletes = NULL; /* head of linked list */
HTAB *pendingSyncHash = NULL;
/*
* RelationCreateStorage
@ -129,32 +118,6 @@ RelationCreateStorage(RelFileNode rnode, char relpersistence)
pending->next = pendingDeletes;
pendingDeletes = pending;
/* Queue an at-commit sync. */
if (relpersistence == RELPERSISTENCE_PERMANENT && !XLogIsNeeded())
{
pendingSync *pending;
bool found;
/* we sync only permanent relations */
Assert(backend == InvalidBackendId);
if (!pendingSyncHash)
{
HASHCTL ctl;
ctl.keysize = sizeof(RelFileNode);
ctl.entrysize = sizeof(pendingSync);
ctl.hcxt = TopTransactionContext;
pendingSyncHash =
hash_create("pending sync hash",
16, &ctl, HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
}
pending = hash_search(pendingSyncHash, &rnode, HASH_ENTER, &found);
Assert(!found);
pending->is_truncated = false;
}
return srel;
}
@ -289,8 +252,6 @@ RelationTruncate(Relation rel, BlockNumber nblocks)
if (vm)
visibilitymap_truncate(rel, nblocks);
RelationPreTruncate(rel);
/*
* We WAL-log the truncation before actually truncating, which means
* trouble if the truncation fails. If we then crash, the WAL replay
@ -333,28 +294,6 @@ RelationTruncate(Relation rel, BlockNumber nblocks)
smgrtruncate(rel->rd_smgr, MAIN_FORKNUM, nblocks);
}
/*
* RelationPreTruncate
* Perform AM-independent work before a physical truncation.
*
* If an access method's relation_nontransactional_truncate does not call
* RelationTruncate(), it must call this before decreasing the table size.
*/
void
RelationPreTruncate(Relation rel)
{
pendingSync *pending;
if (!pendingSyncHash)
return;
RelationOpenSmgr(rel);
pending = hash_search(pendingSyncHash, &(rel->rd_smgr->smgr_rnode.node),
HASH_FIND, NULL);
if (pending)
pending->is_truncated = true;
}
/*
* Copy a fork's data, block by block.
*
@ -385,9 +324,7 @@ RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
/*
* We need to log the copied data in WAL iff WAL archiving/streaming is
* enabled AND it's a permanent relation. This gives the same answer as
* "RelationNeedsWAL(rel) || copying_initfork", because we know the
* current operation created a new relfilenode.
* enabled AND it's a permanent relation.
*/
use_wal = XLogIsNeeded() &&
(relpersistence == RELPERSISTENCE_PERMANENT || copying_initfork);
@ -429,39 +366,24 @@ RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
}
/*
* When we WAL-logged rel pages, we must nonetheless fsync them. The
* reason is that since we're copying outside shared buffers, a CHECKPOINT
* occurring during the copy has no way to flush the previously written
* data to disk (indeed it won't know the new rel even exists). A crash
* later on would replay WAL from the checkpoint, therefore it wouldn't
* replay our earlier WAL entries. If we do not fsync those pages here,
* they might still not be on disk when the crash occurs.
* If the rel is WAL-logged, must fsync before commit. We use heap_sync
* to ensure that the toast table gets fsync'd too. (For a temp or
* unlogged rel we don't care since the data will be gone after a crash
* anyway.)
*
* It's obvious that we must do this when not WAL-logging the copy. It's
* less obvious that we have to do it even if we did WAL-log the copied
* pages. The reason is that since we're copying outside shared buffers, a
* CHECKPOINT occurring during the copy has no way to flush the previously
* written data to disk (indeed it won't know the new rel even exists). A
* crash later on would replay WAL from the checkpoint, therefore it
* wouldn't replay our earlier WAL entries. If we do not fsync those pages
* here, they might still not be on disk when the crash occurs.
*/
if (use_wal || copying_initfork)
if (relpersistence == RELPERSISTENCE_PERMANENT || copying_initfork)
smgrimmedsync(dst, forkNum);
}
/*
* RelFileNodeSkippingWAL - check if a BM_PERMANENT relfilenode is using WAL
*
* Changes of certain relfilenodes must not write WAL; see "Skipping WAL for
* New RelFileNode" in src/backend/access/transam/README. Though it is
* known from Relation efficiently, this function is intended for the code
* paths not having access to Relation.
*/
bool
RelFileNodeSkippingWAL(RelFileNode rnode)
{
if (XLogIsNeeded())
return false; /* no permanent relfilenode skips WAL */
if (!pendingSyncHash ||
hash_search(pendingSyncHash, &rnode, HASH_FIND, NULL) == NULL)
return false;
return true;
}
/*
* smgrDoPendingDeletes() -- Take care of relation deletes at end of xact.
*
@ -539,144 +461,6 @@ smgrDoPendingDeletes(bool isCommit)
}
}
/*
* smgrDoPendingSyncs() -- Take care of relation syncs at end of xact.
*/
void
smgrDoPendingSyncs(bool isCommit)
{
PendingRelDelete *pending;
int nrels = 0,
maxrels = 0;
SMgrRelation *srels = NULL;
HASH_SEQ_STATUS scan;
pendingSync *pendingsync;
if (XLogIsNeeded())
return; /* no relation can use this */
Assert(GetCurrentTransactionNestLevel() == 1);
if (!pendingSyncHash)
return; /* no relation needs sync */
/* Just throw away all pending syncs if any at rollback */
if (!isCommit)
{
pendingSyncHash = NULL;
return;
}
AssertPendingSyncs_RelationCache();
/* Skip syncing nodes that smgrDoPendingDeletes() will delete. */
for (pending = pendingDeletes; pending != NULL; pending = pending->next)
{
if (!pending->atCommit)
continue;
(void) hash_search(pendingSyncHash, (void *) &pending->relnode,
HASH_REMOVE, NULL);
}
hash_seq_init(&scan, pendingSyncHash);
while ((pendingsync = (pendingSync *) hash_seq_search(&scan)))
{
ForkNumber fork;
BlockNumber nblocks[MAX_FORKNUM + 1];
BlockNumber total_blocks = 0;
SMgrRelation srel;
srel = smgropen(pendingsync->rnode, InvalidBackendId);
/*
* We emit newpage WAL records for smaller relations.
*
* Small WAL records have a chance to be emitted along with other
* backends' WAL records. We emit WAL records instead of syncing for
* files that are smaller than a certain threshold, expecting faster
* commit. The threshold is defined by the GUC wal_skip_threshold.
*/
if (!pendingsync->is_truncated)
{
for (fork = 0; fork <= MAX_FORKNUM; fork++)
{
if (smgrexists(srel, fork))
{
BlockNumber n = smgrnblocks(srel, fork);
/* we shouldn't come here for unlogged relations */
Assert(fork != INIT_FORKNUM);
nblocks[fork] = n;
total_blocks += n;
}
else
nblocks[fork] = InvalidBlockNumber;
}
}
/*
* Sync file or emit WAL records for its contents.
*
* Although we emit WAL record if the file is small enough, do file
* sync regardless of the size if the file has experienced a
* truncation. It is because the file would be followed by trailing
* garbage blocks after a crash recovery if, while a past longer file
* had been flushed out, we omitted syncing-out of the file and
* emitted WAL instead. You might think that we could choose WAL if
* the current main fork is longer than ever, but there's a case where
* main fork is longer than ever but FSM fork gets shorter.
*/
if (pendingsync->is_truncated ||
total_blocks * BLCKSZ / 1024 >= wal_skip_threshold)
{
/* allocate the initial array, or extend it, if needed */
if (maxrels == 0)
{
maxrels = 8;
srels = palloc(sizeof(SMgrRelation) * maxrels);
}
else if (maxrels <= nrels)
{
maxrels *= 2;
srels = repalloc(srels, sizeof(SMgrRelation) * maxrels);
}
srels[nrels++] = srel;
}
else
{
/* Emit WAL records for all blocks. The file is small enough. */
for (fork = 0; fork <= MAX_FORKNUM; fork++)
{
int n = nblocks[fork];
Relation rel;
if (!BlockNumberIsValid(n))
continue;
/*
* Emit WAL for the whole file. Unfortunately we don't know
* what kind of a page this is, so we have to log the full
* page including any unused space. ReadBufferExtended()
* counts some pgstat events; unfortunately, we discard them.
*/
rel = CreateFakeRelcacheEntry(srel->smgr_rnode.node);
log_newpage_range(rel, fork, 0, n, false);
FreeFakeRelcacheEntry(rel);
}
}
}
pendingSyncHash = NULL;
if (nrels > 0)
{
smgrdosyncall(srels, nrels);
pfree(srels);
}
}
/*
* smgrGetPendingDeletes() -- Get a list of non-temp relations to be deleted.
*

19
src/backend/commands/cluster.c
View File

@ -1111,25 +1111,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
*mapped_tables++ = r2;
}
/*
* Recognize that rel1's relfilenode (swapped from rel2) is new in this
* subtransaction. The rel2 storage (swapped from rel1) may or may not be
* new.
*/
{
Relation rel1,
rel2;
rel1 = relation_open(r1, NoLock);
rel2 = relation_open(r2, NoLock);
rel2->rd_createSubid = rel1->rd_createSubid;
rel2->rd_newRelfilenodeSubid = rel1->rd_newRelfilenodeSubid;
rel2->rd_firstRelfilenodeSubid = rel1->rd_firstRelfilenodeSubid;
RelationAssumeNewRelfilenode(rel1);
relation_close(rel1, NoLock);
relation_close(rel2, NoLock);
}
/*
* In the case of a shared catalog, these next few steps will only affect
* our own database's pg_class row; but that's okay, because they are all

58
src/backend/commands/copy.c
View File

@ -2715,15 +2715,63 @@ CopyFrom(CopyState cstate)
RelationGetRelationName(cstate->rel))));
}
/*
* If the target file is new-in-transaction, we assume that checking FSM
* for free space is a waste of time. This could possibly be wrong, but
* it's unlikely.
/*----------
* Check to see if we can avoid writing WAL
*
* If archive logging/streaming is not enabled *and* either
* - table was created in same transaction as this COPY
* - data is being written to relfilenode created in this transaction
* then we can skip writing WAL. It's safe because if the transaction
* doesn't commit, we'll discard the table (or the new relfilenode file).
* If it does commit, we'll have done the table_finish_bulk_insert() at
* the bottom of this routine first.
*
* As mentioned in comments in utils/rel.h, the in-same-transaction test
* is not always set correctly, since in rare cases rd_newRelfilenodeSubid
* can be cleared before the end of the transaction. The exact case is
* when a relation sets a new relfilenode twice in same transaction, yet
* the second one fails in an aborted subtransaction, e.g.
*
* BEGIN;
* TRUNCATE t;
* SAVEPOINT save;
* TRUNCATE t;
* ROLLBACK TO save;
* COPY ...
*
* Also, if the target file is new-in-transaction, we assume that checking
* FSM for free space is a waste of time, even if we must use WAL because
* of archiving. This could possibly be wrong, but it's unlikely.
*
* The comments for table_tuple_insert and RelationGetBufferForTuple
* specify that skipping WAL logging is only safe if we ensure that our
* tuples do not go into pages containing tuples from any other
* transactions --- but this must be the case if we have a new table or
* new relfilenode, so we need no additional work to enforce that.
*
* We currently don't support this optimization if the COPY target is a
* partitioned table as we currently only lazily initialize partition
* information when routing the first tuple to the partition. We cannot
* know at this stage if we can perform this optimization. It should be
* possible to improve on this, but it does mean maintaining heap insert
* option flags per partition and setting them when we first open the
* partition.
*
* This optimization is not supported for relation types which do not
* have any physical storage, with foreign tables and views using
* INSTEAD OF triggers entering in this category. Partitioned tables
* are not supported as per the description above.
*----------
*/
/* createSubid is creation check, newRelfilenodeSubid is truncation check */
if (RELKIND_HAS_STORAGE(cstate->rel->rd_rel->relkind) &&
(cstate->rel->rd_createSubid != InvalidSubTransactionId ||
cstate->rel->rd_firstRelfilenodeSubid != InvalidSubTransactionId))
cstate->rel->rd_newRelfilenodeSubid != InvalidSubTransactionId))
{
ti_options |= TABLE_INSERT_SKIP_FSM;
if (!XLogIsNeeded())
ti_options |= TABLE_INSERT_SKIP_WAL;
}
/*
* Optimize if new relfilenode was created in this subxact or one of its

11
src/backend/commands/createas.c
View File

@ -553,13 +553,16 @@ intorel_startup(DestReceiver *self, int operation, TupleDesc typeinfo)
myState->rel = intoRelationDesc;
myState->reladdr = intoRelationAddr;
myState->output_cid = GetCurrentCommandId(true);
myState->ti_options = TABLE_INSERT_SKIP_FSM;
myState->bistate = GetBulkInsertState();
/*
* Valid smgr_targblock implies something already wrote to the relation.
* This may be harmless, but this function hasn't planned for it.
* We can skip WAL-logging the insertions, unless PITR or streaming
* replication is in use. We can skip the FSM in any case.
*/
myState->ti_options = TABLE_INSERT_SKIP_FSM |
(XLogIsNeeded() ? 0 : TABLE_INSERT_SKIP_WAL);
myState->bistate = GetBulkInsertState();
/* Not using WAL requires smgr_targblock be initially invalid */
Assert(RelationGetTargetBlock(intoRelationDesc) == InvalidBlockNumber);
}

2
src/backend/commands/indexcmds.c
View File

@ -1195,8 +1195,6 @@ DefineIndex(Oid relationId,
childStmt->relation = NULL;
childStmt->indexOid = InvalidOid;
childStmt->oldNode = InvalidOid;
childStmt->oldCreateSubid = InvalidSubTransactionId;
childStmt->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
/*
* Adjust any Vars (both in expressions and in the index's

12
src/backend/commands/matview.c
View File

@ -457,13 +457,17 @@ transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo)
*/
myState->transientrel = transientrel;
myState->output_cid = GetCurrentCommandId(true);
myState->ti_options = TABLE_INSERT_SKIP_FSM | TABLE_INSERT_FROZEN;
myState->bistate = GetBulkInsertState();
/*
* Valid smgr_targblock implies something already wrote to the relation.
* This may be harmless, but this function hasn't planned for it.
* We can skip WAL-logging the insertions, unless PITR or streaming
* replication is in use. We can skip the FSM in any case.
*/
myState->ti_options = TABLE_INSERT_SKIP_FSM | TABLE_INSERT_FROZEN;
if (!XLogIsNeeded())
myState->ti_options |= TABLE_INSERT_SKIP_WAL;
myState->bistate = GetBulkInsertState();
/* Not using WAL requires smgr_targblock be initially invalid */
Assert(RelationGetTargetBlock(transientrel) == InvalidBlockNumber);
}

26
src/backend/commands/tablecmds.c
View File

@ -4785,14 +4785,19 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap, LOCKMODE lockmode)
newrel = NULL;
/*
* Prepare a BulkInsertState and options for table_tuple_insert. The FSM
* is empty, so don't bother using it.
* Prepare a BulkInsertState and options for table_tuple_insert. Because
* we're building a new heap, we can skip WAL-logging and fsync it to disk
* at the end instead (unless WAL-logging is required for archiving or
* streaming replication). The FSM is empty too, so don't bother using it.
*/
if (newrel)
{
mycid = GetCurrentCommandId(true);
bistate = GetBulkInsertState();
ti_options = TABLE_INSERT_SKIP_FSM;
if (!XLogIsNeeded())
ti_options |= TABLE_INSERT_SKIP_WAL;
}
else
{
@ -7300,19 +7305,14 @@ ATExecAddIndex(AlteredTableInfo *tab, Relation rel,
/*
* If TryReuseIndex() stashed a relfilenode for us, we used it for the new
* index instead of building from scratch. Restore associated fields.
* This may store InvalidSubTransactionId in both fields, in which case
* relcache.c will assume it can rebuild the relcache entry. Hence, do
* this after the CCI that made catalog rows visible to any rebuild. The
* DROP of the old edition of this index will have scheduled the storage
* for deletion at commit, so cancel that pending deletion.
* index instead of building from scratch. The DROP of the old edition of
* this index will have scheduled the storage for deletion at commit, so
* cancel that pending deletion.
*/
if (OidIsValid(stmt->oldNode))
{
Relation irel = index_open(address.objectId, NoLock);
irel->rd_createSubid = stmt->oldCreateSubid;
irel->rd_firstRelfilenodeSubid = stmt->oldFirstRelfilenodeSubid;
RelationPreserveStorage(irel->rd_node, true);
index_close(irel, NoLock);
}
@ -11619,11 +11619,7 @@ TryReuseIndex(Oid oldId, IndexStmt *stmt)
/* If it's a partitioned index, there is no storage to share. */
if (irel->rd_rel->relkind != RELKIND_PARTITIONED_INDEX)
{
stmt->oldNode = irel->rd_node.relNode;
stmt->oldCreateSubid = irel->rd_createSubid;
stmt->oldFirstRelfilenodeSubid = irel->rd_firstRelfilenodeSubid;
}
index_close(irel, NoLock);
}
}
@ -12557,8 +12553,6 @@ ATExecSetTableSpace(Oid tableOid, Oid newTableSpace, LOCKMODE lockmode)
table_close(pg_class, RowExclusiveLock);
RelationAssumeNewRelfilenode(rel);
relation_close(rel, NoLock);
/* Make sure the reltablespace change is visible */

2
src/backend/nodes/copyfuncs.c
View File

@ -3469,8 +3469,6 @@ _copyIndexStmt(const IndexStmt *from)
COPY_STRING_FIELD(idxcomment);
COPY_SCALAR_FIELD(indexOid);
COPY_SCALAR_FIELD(oldNode);
COPY_SCALAR_FIELD(oldCreateSubid);
COPY_SCALAR_FIELD(oldFirstRelfilenodeSubid);
COPY_SCALAR_FIELD(unique);
COPY_SCALAR_FIELD(primary);
COPY_SCALAR_FIELD(isconstraint);

2
src/backend/nodes/equalfuncs.c
View File

@ -1339,8 +1339,6 @@ _equalIndexStmt(const IndexStmt *a, const IndexStmt *b)
COMPARE_STRING_FIELD(idxcomment);
COMPARE_SCALAR_FIELD(indexOid);
COMPARE_SCALAR_FIELD(oldNode);
COMPARE_SCALAR_FIELD(oldCreateSubid);
COMPARE_SCALAR_FIELD(oldFirstRelfilenodeSubid);
COMPARE_SCALAR_FIELD(unique);
COMPARE_SCALAR_FIELD(primary);
COMPARE_SCALAR_FIELD(isconstraint);

2
src/backend/nodes/outfuncs.c
View File

@ -2642,8 +2642,6 @@ _outIndexStmt(StringInfo str, const IndexStmt *node)
WRITE_STRING_FIELD(idxcomment);
WRITE_OID_FIELD(indexOid);
WRITE_OID_FIELD(oldNode);
WRITE_UINT_FIELD(oldCreateSubid);
WRITE_UINT_FIELD(oldFirstRelfilenodeSubid);
WRITE_BOOL_FIELD(unique);
WRITE_BOOL_FIELD(primary);
WRITE_BOOL_FIELD(isconstraint);

4
src/backend/parser/gram.y
View File

@ -7357,8 +7357,6 @@ IndexStmt: CREATE opt_unique INDEX opt_concurrently opt_index_name
n->idxcomment = NULL;
n->indexOid = InvalidOid;
n->oldNode = InvalidOid;
n->oldCreateSubid = InvalidSubTransactionId;
n->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
n->primary = false;
n->isconstraint = false;
n->deferrable = false;
@ -7387,8 +7385,6 @@ IndexStmt: CREATE opt_unique INDEX opt_concurrently opt_index_name
n->idxcomment = NULL;
n->indexOid = InvalidOid;
n->oldNode = InvalidOid;
n->oldCreateSubid = InvalidSubTransactionId;
n->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
n->primary = false;
n->isconstraint = false;
n->deferrable = false;

4
src/backend/parser/parse_utilcmd.c
View File

@ -1401,8 +1401,6 @@ generateClonedIndexStmt(RangeVar *heapRel, Relation source_idx,
index->idxcomment = NULL;
index->indexOid = InvalidOid;
index->oldNode = InvalidOid;
index->oldCreateSubid = InvalidSubTransactionId;
index->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
index->unique = idxrec->indisunique;
index->primary = idxrec->indisprimary;
index->transformed = true; /* don't need transformIndexStmt */
@ -2001,8 +1999,6 @@ transformIndexConstraint(Constraint *constraint, CreateStmtContext *cxt)
index->idxcomment = NULL;
index->indexOid = InvalidOid;
index->oldNode = InvalidOid;
index->oldCreateSubid = InvalidSubTransactionId;
index->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
index->transformed = false;
index->concurrent = false;
index->if_not_exists = false;

125
src/backend/storage/buffer/bufmgr.c
View File

@ -66,7 +66,7 @@
#define BUF_WRITTEN 0x01
#define BUF_REUSABLE 0x02
#define RELS_BSEARCH_THRESHOLD 20
#define DROP_RELS_BSEARCH_THRESHOLD 20
typedef struct PrivateRefCountEntry
{
@ -105,19 +105,6 @@ typedef struct CkptTsStatus
int index;
} CkptTsStatus;
/*
* Type for array used to sort SMgrRelations
*
* FlushRelationsAllBuffers shares the same comparator function with
* DropRelFileNodesAllBuffers. Pointer to this struct and RelFileNode must be
* compatible.
*/
typedef struct SMgrSortArray
{
RelFileNode rnode; /* This must be the first member */
SMgrRelation srel;
} SMgrSortArray;
/* GUC variables */
bool zero_damaged_pages = false;
int bgwriter_lru_maxpages = 100;
@ -3033,7 +3020,7 @@ DropRelFileNodesAllBuffers(RelFileNodeBackend *rnodes, int nnodes)
* an exactly determined value, as it depends on many factors (CPU and RAM
* speeds, amount of shared buffers etc.).
*/
use_bsearch = n > RELS_BSEARCH_THRESHOLD;
use_bsearch = n > DROP_RELS_BSEARCH_THRESHOLD;
/* sort the list of rnodes if necessary */
if (use_bsearch)
@ -3283,104 +3270,6 @@ FlushRelationBuffers(Relation rel)
}
}
/* ---------------------------------------------------------------------
* FlushRelationsAllBuffers
*
* This function flushes out of the buffer pool all the pages of all
* forks of the specified smgr relations. It's equivalent to calling
* FlushRelationBuffers once per fork per relation. The relations are
* assumed not to use local buffers.
* --------------------------------------------------------------------
*/
void
FlushRelationsAllBuffers(SMgrRelation *smgrs, int nrels)
{
int i;
SMgrSortArray *srels;
bool use_bsearch;
if (nrels == 0)
return;
/* fill-in array for qsort */
srels = palloc(sizeof(SMgrSortArray) * nrels);
for (i = 0; i < nrels; i++)
{
Assert(!RelFileNodeBackendIsTemp(smgrs[i]->smgr_rnode));
srels[i].rnode = smgrs[i]->smgr_rnode.node;
srels[i].srel = smgrs[i];
}
/*
* Save the bsearch overhead for low number of relations to sync. See
* DropRelFileNodesAllBuffers for details.
*/
use_bsearch = nrels > RELS_BSEARCH_THRESHOLD;
/* sort the list of SMgrRelations if necessary */
if (use_bsearch)
pg_qsort(srels, nrels, sizeof(SMgrSortArray), rnode_comparator);
/* Make sure we can handle the pin inside the loop */
ResourceOwnerEnlargeBuffers(CurrentResourceOwner);
for (i = 0; i < NBuffers; i++)
{
SMgrSortArray *srelent = NULL;
BufferDesc *bufHdr = GetBufferDescriptor(i);
uint32 buf_state;
/*
* As in DropRelFileNodeBuffers, an unlocked precheck should be safe
* and saves some cycles.
*/
if (!use_bsearch)
{
int j;
for (j = 0; j < nrels; j++)
{
if (RelFileNodeEquals(bufHdr->tag.rnode, srels[j].rnode))
{
srelent = &srels[j];
break;
}
}
}
else
{
srelent = bsearch((const void *) &(bufHdr->tag.rnode),
srels, nrels, sizeof(SMgrSortArray),
rnode_comparator);
}
/* buffer doesn't belong to any of the given relfilenodes; skip it */
if (srelent == NULL)
continue;
ReservePrivateRefCountEntry();
buf_state = LockBufHdr(bufHdr);
if (RelFileNodeEquals(bufHdr->tag.rnode, srelent->rnode) &&
(buf_state & (BM_VALID | BM_DIRTY)) == (BM_VALID | BM_DIRTY))
{
PinBuffer_Locked(bufHdr);
LWLockAcquire(BufferDescriptorGetContentLock(bufHdr), LW_SHARED);
FlushBuffer(bufHdr, srelent->srel);
LWLockRelease(BufferDescriptorGetContentLock(bufHdr));
UnpinBuffer(bufHdr, true);
}
else
UnlockBufHdr(bufHdr, buf_state);
}
pfree(srels);
}
/* ---------------------------------------------------------------------
* FlushDatabaseBuffers
*
@ -3582,15 +3471,13 @@ MarkBufferDirtyHint(Buffer buffer, bool buffer_std)
(pg_atomic_read_u32(&bufHdr->state) & BM_PERMANENT))
{
/*
* If we must not write WAL, due to a relfilenode-specific
* condition or being in recovery, don't dirty the page. We can
* set the hint, just not dirty the page as a result so the hint
* is lost when we evict the page or shutdown.
* If we're in recovery we cannot dirty a page because of a hint.
* We can set the hint, just not dirty the page as a result so the
* hint is lost when we evict the page or shutdown.
*
* See src/backend/storage/page/README for longer discussion.
*/
if (RecoveryInProgress() ||
RelFileNodeSkippingWAL(bufHdr->tag.rnode))
if (RecoveryInProgress())
return;
/*

12
src/backend/storage/lmgr/lock.c
View File

@ -587,18 +587,6 @@ LockHeldByMe(const LOCKTAG *locktag, LOCKMODE lockmode)
return (locallock && locallock->nLocks > 0);
}
#ifdef USE_ASSERT_CHECKING
/*
* GetLockMethodLocalHash -- return the hash of local locks, for modules that
* evaluate assertions based on all locks held.
*/
HTAB *
GetLockMethodLocalHash(void)
{
return LockMethodLocalHash;
}
#endif
/*
* LockHasWaiters -- look up 'locktag' and check if releasing this
* lock would wake up other processes waiting for it.

36
src/backend/storage/smgr/md.c
View File

@ -234,10 +234,11 @@ mdcreate(SMgrRelation reln, ForkNumber forkNum, bool isRedo)
* During replay, we would delete the file and then recreate it, which is fine
* if the contents of the file were repopulated by subsequent WAL entries.
* But if we didn't WAL-log insertions, but instead relied on fsyncing the
* file after populating it (as we do at wal_level=minimal), the contents of
* the file would be lost forever. By leaving the empty file until after the
* next checkpoint, we prevent reassignment of the relfilenode number until
* it's safe, because relfilenode assignment skips over any existing file.
* file after populating it (as for instance CLUSTER and CREATE INDEX do),
* the contents of the file would be lost forever. By leaving the empty file
* until after the next checkpoint, we prevent reassignment of the relfilenode
* number until it's safe, because relfilenode assignment skips over any
* existing file.
*
* We do not need to go through this dance for temp relations, though, because
* we never make WAL entries for temp rels, and so a temp rel poses no threat
@ -851,18 +852,12 @@ mdtruncate(SMgrRelation reln, ForkNumber forknum, BlockNumber nblocks)
* mdimmedsync() -- Immediately sync a relation to stable storage.
*
* Note that only writes already issued are synced; this routine knows
* nothing of dirty buffers that may exist inside the buffer manager. We
* sync active and inactive segments; smgrDoPendingSyncs() relies on this.
* Consider a relation skipping WAL. Suppose a checkpoint syncs blocks of
* some segment, then mdtruncate() renders that segment inactive. If we
* crash before the next checkpoint syncs the newly-inactive segment, that
* segment may survive recovery, reintroducing unwanted data into the table.
* nothing of dirty buffers that may exist inside the buffer manager.
*/
void
mdimmedsync(SMgrRelation reln, ForkNumber forknum)
{
int segno;
int min_inactive_seg;
/*
* NOTE: mdnblocks makes sure we have opened all active segments, so that
@ -870,16 +865,7 @@ mdimmedsync(SMgrRelation reln, ForkNumber forknum)
*/
mdnblocks(reln, forknum);
min_inactive_seg = segno = reln->md_num_open_segs[forknum];
/*
* Temporarily open inactive segments, then close them after sync. There
* may be some inactive segments left opened after fsync() error, but that
* is harmless. We don't bother to clean them up and take a risk of
* further trouble. The next mdclose() will soon close them.
*/
while (_mdfd_openseg(reln, forknum, segno, 0) != NULL)
segno++;
segno = reln->md_num_open_segs[forknum];
while (segno > 0)
{
@ -890,14 +876,6 @@ mdimmedsync(SMgrRelation reln, ForkNumber forknum)
(errcode_for_file_access(),
errmsg("could not fsync file \"%s\": %m",
FilePathName(v->mdfd_vfd))));
/* Close inactive segments immediately */
if (segno > min_inactive_seg)
{
FileClose(v->mdfd_vfd);
_fdvec_resize(reln, forknum, segno - 1);
}
segno--;
}
}

35
src/backend/storage/smgr/smgr.c
View File

@ -416,41 +416,6 @@ smgrdounlink(SMgrRelation reln, bool isRedo)
smgrsw[which].smgr_unlink(rnode, InvalidForkNumber, isRedo);
}
/*
* smgrdosyncall() -- Immediately sync all forks of all given relations
*
* All forks of all given relations are synced out to the store.
*
* This is equivalent to FlushRelationBuffers() for each smgr relation,
* then calling smgrimmedsync() for all forks of each relation, but it's
* significantly quicker so should be preferred when possible.
*/
void
smgrdosyncall(SMgrRelation *rels, int nrels)
{
int i = 0;
ForkNumber forknum;
if (nrels == 0)
return;
FlushRelationsAllBuffers(rels, nrels);
/*
* Sync the physical file(s).
*/
for (i = 0; i < nrels; i++)
{
int which = rels[i]->smgr_which;
for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
{
if (smgrsw[which].smgr_exists(rels[i], forknum))
smgrsw[which].smgr_immedsync(rels[i], forknum);
}
}
}
/*
* smgrdounlinkall() -- Immediately unlink all forks of all given relations
*

268
src/backend/utils/cache/relcache.c vendored
View File

@ -263,9 +263,6 @@ static void RelationReloadIndexInfo(Relation relation);
static void RelationReloadNailed(Relation relation);
static void RelationFlushRelation(Relation relation);
static void RememberToFreeTupleDescAtEOX(TupleDesc td);
#ifdef USE_ASSERT_CHECKING
static void AssertPendingSyncConsistency(Relation relation);
#endif
static void AtEOXact_cleanup(Relation relation, bool isCommit);
static void AtEOSubXact_cleanup(Relation relation, bool isCommit,
SubTransactionId mySubid, SubTransactionId parentSubid);
@ -1100,8 +1097,6 @@ RelationBuildDesc(Oid targetRelId, bool insertIt)
relation->rd_isnailed = false;
relation->rd_createSubid = InvalidSubTransactionId;
relation->rd_newRelfilenodeSubid = InvalidSubTransactionId;
relation->rd_firstRelfilenodeSubid = InvalidSubTransactionId;
relation->rd_droppedSubid = InvalidSubTransactionId;
switch (relation->rd_rel->relpersistence)
{
case RELPERSISTENCE_UNLOGGED:
@ -1835,8 +1830,6 @@ formrdesc(const char *relationName, Oid relationReltype,
relation->rd_isnailed = true;
relation->rd_createSubid = InvalidSubTransactionId;
relation->rd_newRelfilenodeSubid = InvalidSubTransactionId;
relation->rd_firstRelfilenodeSubid = InvalidSubTransactionId;
relation->rd_droppedSubid = InvalidSubTransactionId;
relation->rd_backend = InvalidBackendId;
relation->rd_islocaltemp = false;
@ -2009,13 +2002,6 @@ RelationIdGetRelation(Oid relationId)
if (RelationIsValid(rd))
{
/* return NULL for dropped relations */
if (rd->rd_droppedSubid != InvalidSubTransactionId)
{
Assert(!rd->rd_isvalid);
return NULL;
}
RelationIncrementReferenceCount(rd);
/* revalidate cache entry if necessary */
if (!rd->rd_isvalid)
@ -2109,7 +2095,7 @@ RelationClose(Relation relation)
#ifdef RELCACHE_FORCE_RELEASE
if (RelationHasReferenceCountZero(relation) &&
relation->rd_createSubid == InvalidSubTransactionId &&
relation->rd_firstRelfilenodeSubid == InvalidSubTransactionId)
relation->rd_newRelfilenodeSubid == InvalidSubTransactionId)
RelationClearRelation(relation, false);
#endif
}
@ -2148,11 +2134,10 @@ RelationReloadIndexInfo(Relation relation)
HeapTuple pg_class_tuple;
Form_pg_class relp;
/* Should be called only for invalidated, live indexes */
/* Should be called only for invalidated indexes */
Assert((relation->rd_rel->relkind == RELKIND_INDEX ||
relation->rd_rel->relkind == RELKIND_PARTITIONED_INDEX) &&
!relation->rd_isvalid &&
relation->rd_droppedSubid == InvalidSubTransactionId);
!relation->rd_isvalid);
/* Ensure it's closed at smgr level */
RelationCloseSmgr(relation);
@ -2448,13 +2433,6 @@ RelationClearRelation(Relation relation, bool rebuild)
return;
}
/* Mark it invalid until we've finished rebuild */
relation->rd_isvalid = false;
/* See RelationForgetRelation(). */
if (relation->rd_droppedSubid != InvalidSubTransactionId)
return;
/*
* Even non-system indexes should not be blown away if they are open and
* have valid index support information. This avoids problems with active
@ -2467,11 +2445,15 @@ RelationClearRelation(Relation relation, bool rebuild)
relation->rd_refcnt > 0 &&
relation->rd_indexcxt != NULL)
{
relation->rd_isvalid = false; /* needs to be revalidated */
if (IsTransactionState())
RelationReloadIndexInfo(relation);
return;
}
/* Mark it invalid until we've finished rebuild */
relation->rd_isvalid = false;
/*
* If we're really done with the relcache entry, blow it away. But if
* someone is still using it, reconstruct the whole deal without moving
@ -2529,13 +2511,13 @@ RelationClearRelation(Relation relation, bool rebuild)
* problem.
*
* When rebuilding an open relcache entry, we must preserve ref count,
* rd_*Subid, and rd_toastoid state. Also attempt to preserve the
* pg_class entry (rd_rel), tupledesc, rewrite-rule, partition key,
* and partition descriptor substructures in place, because various
* places assume that these structures won't move while they are
* working with an open relcache entry. (Note: the refcount
* mechanism for tupledescs might someday allow us to remove this hack
* for the tupledesc.)
* rd_createSubid/rd_newRelfilenodeSubid, and rd_toastoid state. Also
* attempt to preserve the pg_class entry (rd_rel), tupledesc,
* rewrite-rule, partition key, and partition descriptor substructures
* in place, because various places assume that these structures won't
* move while they are working with an open relcache entry. (Note:
* the refcount mechanism for tupledescs might someday allow us to
* remove this hack for the tupledesc.)
*
* Note that this process does not touch CurrentResourceOwner; which
* is good because whatever ref counts the entry may have do not
@ -2619,8 +2601,6 @@ RelationClearRelation(Relation relation, bool rebuild)
/* creation sub-XIDs must be preserved */
SWAPFIELD(SubTransactionId, rd_createSubid);
SWAPFIELD(SubTransactionId, rd_newRelfilenodeSubid);
SWAPFIELD(SubTransactionId, rd_firstRelfilenodeSubid);
SWAPFIELD(SubTransactionId, rd_droppedSubid);
/* un-swap rd_rel pointers, swap contents instead */
SWAPFIELD(Form_pg_class, rd_rel);
/* ... but actually, we don't have to update newrel->rd_rel */
@ -2688,12 +2668,12 @@ static void
RelationFlushRelation(Relation relation)
{
if (relation->rd_createSubid != InvalidSubTransactionId ||
relation->rd_firstRelfilenodeSubid != InvalidSubTransactionId)
relation->rd_newRelfilenodeSubid != InvalidSubTransactionId)
{
/*
* New relcache entries are always rebuilt, not flushed; else we'd
* forget the "new" status of the relation. Ditto for the
* new-relfilenode status.
* forget the "new" status of the relation, which is a useful
* optimization to have. Ditto for the new-relfilenode status.
*
* The rel could have zero refcnt here, so temporarily increment the
* refcnt to ensure it's safe to rebuild it. We can assume that the
@ -2715,7 +2695,10 @@ RelationFlushRelation(Relation relation)
}
/*
* RelationForgetRelation - caller reports that it dropped the relation
* RelationForgetRelation - unconditionally remove a relcache entry
*
* External interface for destroying a relcache entry when we
* drop the relation.
*/
void
RelationForgetRelation(Oid rid)
@ -2730,19 +2713,7 @@ RelationForgetRelation(Oid rid)
if (!RelationHasReferenceCountZero(relation))
elog(ERROR, "relation %u is still open", rid);
Assert(relation->rd_droppedSubid == InvalidSubTransactionId);
if (relation->rd_createSubid != InvalidSubTransactionId ||
relation->rd_firstRelfilenodeSubid != InvalidSubTransactionId)
{
/*
* In the event of subtransaction rollback, we must not forget
* rd_*Subid. Mark the entry "dropped" so RelationClearRelation()
* invalidates it in lieu of destroying it. (If we're in a top
* transaction, we could opt to destroy the entry.)
*/
relation->rd_droppedSubid = GetCurrentSubTransactionId();
}
/* Unconditionally destroy the relcache entry */
RelationClearRelation(relation, false);
}
@ -2782,10 +2753,11 @@ RelationCacheInvalidateEntry(Oid relationId)
* relation cache and re-read relation mapping data.
*
* This is currently used only to recover from SI message buffer overflow,
* so we do not touch relations having new-in-transaction relfilenodes; they
* cannot be targets of cross-backend SI updates (and our own updates now go
* through a separate linked list that isn't limited by the SI message
* buffer size).
* so we do not touch new-in-transaction relations; they cannot be targets
* of cross-backend SI updates (and our own updates now go through a
* separate linked list that isn't limited by the SI message buffer size).
* Likewise, we need not discard new-relfilenode-in-transaction hints,
* since any invalidation of those would be a local event.
*
* We do this in two phases: the first pass deletes deletable items, and
* the second one rebuilds the rebuildable items. This is essential for
@ -2836,7 +2808,7 @@ RelationCacheInvalidate(void)
* pending invalidations.
*/
if (relation->rd_createSubid != InvalidSubTransactionId ||
relation->rd_firstRelfilenodeSubid != InvalidSubTransactionId)
relation->rd_newRelfilenodeSubid != InvalidSubTransactionId)
continue;
relcacheInvalsReceived++;
@ -2948,84 +2920,6 @@ RememberToFreeTupleDescAtEOX(TupleDesc td)
EOXactTupleDescArray[NextEOXactTupleDescNum++] = td;
}
#ifdef USE_ASSERT_CHECKING
static void
AssertPendingSyncConsistency(Relation relation)
{
bool relcache_verdict =
relation->rd_rel->relpersistence == RELPERSISTENCE_PERMANENT &&
((relation->rd_createSubid != InvalidSubTransactionId &&
RELKIND_HAS_STORAGE(relation->rd_rel->relkind)) ||
relation->rd_firstRelfilenodeSubid != InvalidSubTransactionId);
Assert(relcache_verdict == RelFileNodeSkippingWAL(relation->rd_node));
if (relation->rd_droppedSubid != InvalidSubTransactionId)
Assert(!relation->rd_isvalid &&
(relation->rd_createSubid != InvalidSubTransactionId ||
relation->rd_firstRelfilenodeSubid != InvalidSubTransactionId));
}
/*
* AssertPendingSyncs_RelationCache
*
* Assert that relcache.c and storage.c agree on whether to skip WAL.
*/
void
AssertPendingSyncs_RelationCache(void)
{
HASH_SEQ_STATUS status;
LOCALLOCK *locallock;
Relation *rels;
int maxrels;
int nrels;
RelIdCacheEnt *idhentry;
int i;
/*
* Open every relation that this transaction has locked. If, for some
* relation, storage.c is skipping WAL and relcache.c is not skipping WAL,
* a CommandCounterIncrement() typically yields a local invalidation
* message that destroys the relcache entry. By recreating such entries
* here, we detect the problem.
*/
PushActiveSnapshot(GetTransactionSnapshot());
maxrels = 1;
rels = palloc(maxrels * sizeof(*rels));
nrels = 0;
hash_seq_init(&status, GetLockMethodLocalHash());
while ((locallock = (LOCALLOCK *) hash_seq_search(&status)) != NULL)
{
Oid relid;
Relation r;
if (locallock->nLocks <= 0)
continue;
if ((LockTagType) locallock->tag.lock.locktag_type !=
LOCKTAG_RELATION)
continue;
relid = ObjectIdGetDatum(locallock->tag.lock.locktag_field2);
r = RelationIdGetRelation(relid);
if (!RelationIsValid(r))
continue;
if (nrels >= maxrels)
{
maxrels *= 2;
rels = repalloc(rels, maxrels * sizeof(*rels));
}
rels[nrels++] = r;
}
hash_seq_init(&status, RelationIdCache);
while ((idhentry = (RelIdCacheEnt *) hash_seq_search(&status)) != NULL)
AssertPendingSyncConsistency(idhentry->reldesc);
for (i = 0; i < nrels; i++)
RelationClose(rels[i]);
PopActiveSnapshot();
}
#endif
/*
* AtEOXact_RelationCache
*
@ -3108,8 +3002,6 @@ AtEOXact_RelationCache(bool isCommit)
static void
AtEOXact_cleanup(Relation relation, bool isCommit)
{
bool clear_relcache = false;
/*
* The relcache entry's ref count should be back to its normal
* not-in-a-transaction state: 0 unless it's nailed in cache.
@ -3135,31 +3027,17 @@ AtEOXact_cleanup(Relation relation, bool isCommit)
#endif
/*
* Is the relation live after this transaction ends?
* Is it a relation created in the current transaction?
*
* During commit, clear the relcache entry if it is preserved after
* relation drop, in order not to orphan the entry. During rollback,
* clear the relcache entry if the relation is created in the current
* transaction since it isn't interesting any longer once we are out of
* the transaction.
* During commit, reset the flag to zero, since we are now out of the
* creating transaction. During abort, simply delete the relcache entry
* --- it isn't interesting any longer.
*/
clear_relcache =
(isCommit ?
relation->rd_droppedSubid != InvalidSubTransactionId :
relation->rd_createSubid != InvalidSubTransactionId);
/*
* Since we are now out of the transaction, reset the subids to zero.
* That also lets RelationClearRelation() drop the relcache entry.
*/
relation->rd_createSubid = InvalidSubTransactionId;
relation->rd_newRelfilenodeSubid = InvalidSubTransactionId;
relation->rd_firstRelfilenodeSubid = InvalidSubTransactionId;
relation->rd_droppedSubid = InvalidSubTransactionId;
if (clear_relcache)
if (relation->rd_createSubid != InvalidSubTransactionId)
{
if (RelationHasReferenceCountZero(relation))
if (isCommit)
relation->rd_createSubid = InvalidSubTransactionId;
else if (RelationHasReferenceCountZero(relation))
{
RelationClearRelation(relation, false);
return;
@ -3174,10 +3052,16 @@ AtEOXact_cleanup(Relation relation, bool isCommit)
* eventually. This must be just a WARNING to avoid
* error-during-error-recovery loops.
*/
relation->rd_createSubid = InvalidSubTransactionId;
elog(WARNING, "cannot remove relcache entry for \"%s\" because it has nonzero refcount",
RelationGetRelationName(relation));
}
}
/*
* Likewise, reset the hint about the relfilenode being new.
*/
relation->rd_newRelfilenodeSubid = InvalidSubTransactionId;
}
/*
@ -3241,28 +3125,15 @@ AtEOSubXact_cleanup(Relation relation, bool isCommit,
/*
* Is it a relation created in the current subtransaction?
*
* During subcommit, mark it as belonging to the parent, instead, as long
* as it has not been dropped. Otherwise simply delete the relcache entry.
* --- it isn't interesting any longer.
* During subcommit, mark it as belonging to the parent, instead. During
* subabort, simply delete the relcache entry.
*/
if (relation->rd_createSubid == mySubid)
{
/*
* Valid rd_droppedSubid means the corresponding relation is dropped
* but the relcache entry is preserved for at-commit pending sync. We
* need to drop it explicitly here not to make the entry orphan.
*/
Assert(relation->rd_droppedSubid == mySubid ||
relation->rd_droppedSubid == InvalidSubTransactionId);
if (isCommit && relation->rd_droppedSubid == InvalidSubTransactionId)
if (isCommit)
relation->rd_createSubid = parentSubid;
else if (RelationHasReferenceCountZero(relation))
{
/* allow the entry to be removed */
relation->rd_createSubid = InvalidSubTransactionId;
relation->rd_newRelfilenodeSubid = InvalidSubTransactionId;
relation->rd_firstRelfilenodeSubid = InvalidSubTransactionId;
relation->rd_droppedSubid = InvalidSubTransactionId;
RelationClearRelation(relation, false);
return;
}
@ -3282,8 +3153,7 @@ AtEOSubXact_cleanup(Relation relation, bool isCommit,
}
/*
* Likewise, update or drop any new-relfilenode-in-subtransaction record
* or drop record.
* Likewise, update or drop any new-relfilenode-in-subtransaction hint.
*/
if (relation->rd_newRelfilenodeSubid == mySubid)
{
@ -3292,22 +3162,6 @@ AtEOSubXact_cleanup(Relation relation, bool isCommit,
else
relation->rd_newRelfilenodeSubid = InvalidSubTransactionId;
}
if (relation->rd_firstRelfilenodeSubid == mySubid)
{
if (isCommit)
relation->rd_firstRelfilenodeSubid = parentSubid;
else
relation->rd_firstRelfilenodeSubid = InvalidSubTransactionId;
}
if (relation->rd_droppedSubid == mySubid)
{
if (isCommit)
relation->rd_droppedSubid = parentSubid;
else
relation->rd_droppedSubid = InvalidSubTransactionId;
}
}
@ -3397,7 +3251,6 @@ RelationBuildLocalRelation(const char *relname,
/* it's being created in this transaction */
rel->rd_createSubid = GetCurrentSubTransactionId();
rel->rd_newRelfilenodeSubid = InvalidSubTransactionId;
rel->rd_firstRelfilenodeSubid = InvalidSubTransactionId;
/*
* create a new tuple descriptor from the one passed in. We do this
@ -3695,29 +3548,14 @@ RelationSetNewRelfilenode(Relation relation, char persistence)
*/
CommandCounterIncrement();
RelationAssumeNewRelfilenode(relation);
}
/*
* RelationAssumeNewRelfilenode
*
* Code that modifies pg_class.reltablespace or pg_class.relfilenode must call
* this. The call shall precede any code that might insert WAL records whose
* replay would modify bytes in the new RelFileNode, and the call shall follow
* any WAL modifying bytes in the prior RelFileNode. See struct RelationData.
* Ideally, call this as near as possible to the CommandCounterIncrement()
* that makes the pg_class change visible (before it or after it); that
* minimizes the chance of future development adding a forbidden WAL insertion
* between RelationAssumeNewRelfilenode() and CommandCounterIncrement().
*/
void
RelationAssumeNewRelfilenode(Relation relation)
{
/*
* Mark the rel as having been given a new relfilenode in the current
* (sub) transaction. This is a hint that can be used to optimize later
* operations on the rel in the same transaction.
*/
relation->rd_newRelfilenodeSubid = GetCurrentSubTransactionId();
if (relation->rd_firstRelfilenodeSubid == InvalidSubTransactionId)
relation->rd_firstRelfilenodeSubid = relation->rd_newRelfilenodeSubid;
/* Flag relation as needing eoxact cleanup (to clear these fields) */
/* Flag relation as needing eoxact cleanup (to remove the hint) */
EOXactListAdd(relation);
}
@ -5830,8 +5668,6 @@ load_relcache_init_file(bool shared)
rel->rd_fkeylist = NIL;
rel->rd_createSubid = InvalidSubTransactionId;
rel->rd_newRelfilenodeSubid = InvalidSubTransactionId;
rel->rd_firstRelfilenodeSubid = InvalidSubTransactionId;
rel->rd_droppedSubid = InvalidSubTransactionId;
rel->rd_amcache = NULL;
MemSet(&rel->pgstat_info, 0, sizeof(rel->pgstat_info));

12
src/backend/utils/misc/guc.c
View File

@ -36,7 +36,6 @@
#include "access/xlog_internal.h"
#include "catalog/namespace.h"
#include "catalog/pg_authid.h"
#include "catalog/storage.h"
#include "commands/async.h"
#include "commands/prepare.h"
#include "commands/user.h"
@ -2633,17 +2632,6 @@ static struct config_int ConfigureNamesInt[] =
NULL, NULL, NULL
},
{
{"wal_skip_threshold", PGC_USERSET, WAL_SETTINGS,
gettext_noop("Size of new file to fsync instead of writing WAL."),
NULL,
GUC_UNIT_KB
},
&wal_skip_threshold,
2048, 0, MAX_KILOBYTES,
NULL, NULL, NULL
},
{
{"max_wal_senders", PGC_POSTMASTER, REPLICATION_SENDING,
gettext_noop("Sets the maximum number of simultaneously running WAL sender processes."),

1
src/backend/utils/misc/postgresql.conf.sample
View File

@ -214,7 +214,6 @@
# (change requires restart)
#wal_writer_delay = 200ms # 1-10000 milliseconds
#wal_writer_flush_after = 1MB # measured in pages, 0 disables
#wal_skip_threshold = 2MB
#commit_delay = 0 # range 0-100000, in microseconds
#commit_siblings = 5 # range 1-1000