agora inbox for [email protected]
help / color / mirror / Atom feedFrom: Kyotaro Horiguchi <[email protected]>
Subject: [PATCH 2/2] Fix WAL skipping feature
Date: Mon, 20 May 2019 15:38:59 +0900
This patch shows a PoC of how change WAL-skipping feature to avoid
table corruption caused by mixing wal-logged and wal-skipped
operations.
---
src/backend/access/heap/heapam.c | 4 ++--
src/backend/access/heap/heapam_handler.c | 7 +------
src/backend/access/heap/rewriteheap.c | 3 ---
src/backend/access/transam/xact.c | 6 ++++++
src/backend/commands/copy.c | 4 ----
src/backend/commands/createas.c | 3 +--
src/backend/commands/tablecmds.c | 2 --
src/backend/utils/cache/relcache.c | 22 ++++++++++++++++++++++
src/include/access/heapam.h | 1 -
src/include/utils/rel.h | 3 ++-
src/include/utils/relcache.h | 1 +
11 files changed, 35 insertions(+), 21 deletions(-)
diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index 19d2c529d8..dda76c8736 100644
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -1950,7 +1950,7 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid,
MarkBufferDirty(buffer);
/* XLOG stuff */
- if (!(options & HEAP_INSERT_SKIP_WAL) && RelationNeedsWAL(relation))
+ if (RelationNeedsWAL(relation))
{
xl_heap_insert xlrec;
xl_heap_header xlhdr;
@@ -2133,7 +2133,7 @@ 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 = !(options & HEAP_INSERT_SKIP_WAL) && RelationNeedsWAL(relation);
+ needwal = RelationNeedsWAL(relation);
saveFreeSpace = RelationGetTargetPageFreeSpace(relation,
HEAP_DEFAULT_FILLFACTOR);
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 8d8161fd97..f4af981a35 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -560,12 +560,7 @@ tuple_lock_retry:
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);
+ /* heapam doesn't need do this */
}
diff --git a/src/backend/access/heap/rewriteheap.c b/src/backend/access/heap/rewriteheap.c
index bce4274362..1ac77f7c14 100644
--- a/src/backend/access/heap/rewriteheap.c
+++ b/src/backend/access/heap/rewriteheap.c
@@ -654,9 +654,6 @@ 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
diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 20feeec327..fb35992a13 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -2133,6 +2133,9 @@ CommitTransaction(void)
/* Commit updates to the relation map --- do this as late as possible */
AtEOXact_RelationMap(true, is_parallel_worker);
+ /* Perform pending flush */
+ AtEOXact_DoPendingFlush();
+
/*
* set the current transaction state information appropriately during
* commit processing
@@ -2349,6 +2352,9 @@ PrepareTransaction(void)
*/
PreCommit_CheckForSerializationFailure();
+ /* Perform pending flush */
+ AtEOXact_DoPendingFlush();
+
/* NOTIFY will be handled below */
/*
diff --git a/src/backend/commands/copy.c b/src/backend/commands/copy.c
index 6ffc3a62f6..9bae04b8a7 100644
--- a/src/backend/commands/copy.c
+++ b/src/backend/commands/copy.c
@@ -2761,11 +2761,7 @@ CopyFrom(CopyState cstate)
if (RELKIND_HAS_STORAGE(cstate->rel->rd_rel->relkind) &&
(cstate->rel->rd_createSubid != 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
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 43c2fa9124..83e5f9220f 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -558,8 +558,7 @@ intorel_startup(DestReceiver *self, int operation, TupleDesc typeinfo)
* 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->ti_options = TABLE_INSERT_SKIP_FSM;
myState->bistate = GetBulkInsertState();
/* Not using WAL requires smgr_targblock be initially invalid */
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index bfcf9472d7..b686497443 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -4741,8 +4741,6 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap, LOCKMODE lockmode)
bistate = GetBulkInsertState();
ti_options = TABLE_INSERT_SKIP_FSM;
- if (!XLogIsNeeded())
- ti_options |= TABLE_INSERT_SKIP_WAL;
}
else
{
diff --git a/src/backend/utils/cache/relcache.c b/src/backend/utils/cache/relcache.c
index d0f6f715e6..10fd405171 100644
--- a/src/backend/utils/cache/relcache.c
+++ b/src/backend/utils/cache/relcache.c
@@ -2913,6 +2913,28 @@ RememberToFreeTupleDescAtEOX(TupleDesc td)
EOXactTupleDescArray[NextEOXactTupleDescNum++] = td;
}
+void
+AtEOXact_DoPendingFlush()
+{
+ HASH_SEQ_STATUS status;
+ RelIdCacheEnt *idhentry;
+
+ if (!RelationIdCache)
+ return;
+
+ hash_seq_init(&status, RelationIdCache);
+ while ((idhentry = (RelIdCacheEnt *) hash_seq_search(&status)) != NULL)
+ {
+ Relation rel = idhentry->reldesc;
+ if (RELATION_IS_LOCAL(rel) && !XLogIsNeeded() && rel->rd_smgr)
+ {
+ FlushRelationBuffers(rel);
+ smgrimmedsync(rel->rd_smgr, MAIN_FORKNUM);
+ }
+ }
+}
+
+
/*
* AtEOXact_RelationCache
*
diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h
index 62aaa08eff..0fb7d86bf2 100644
--- a/src/include/access/heapam.h
+++ b/src/include/access/heapam.h
@@ -29,7 +29,6 @@
/* "options" flag bits for heap_insert */
-#define HEAP_INSERT_SKIP_WAL TABLE_INSERT_SKIP_WAL
#define HEAP_INSERT_SKIP_FSM TABLE_INSERT_SKIP_FSM
#define HEAP_INSERT_FROZEN TABLE_INSERT_FROZEN
#define HEAP_INSERT_NO_LOGICAL TABLE_INSERT_NO_LOGICAL
diff --git a/src/include/utils/rel.h b/src/include/utils/rel.h
index d7f33abce3..41ab634ff5 100644
--- a/src/include/utils/rel.h
+++ b/src/include/utils/rel.h
@@ -514,7 +514,8 @@ typedef struct ViewOptions
* True if relation needs WAL.
*/
#define RelationNeedsWAL(relation) \
- ((relation)->rd_rel->relpersistence == RELPERSISTENCE_PERMANENT)
+ ((relation)->rd_rel->relpersistence == RELPERSISTENCE_PERMANENT && \
+ !(RELATION_IS_LOCAL(relation) && !XLogIsNeeded()))
/*
* RelationUsesLocalBuffers
diff --git a/src/include/utils/relcache.h b/src/include/utils/relcache.h
index 364495a5f0..cd9b1a6f68 100644
--- a/src/include/utils/relcache.h
+++ b/src/include/utils/relcache.h
@@ -123,6 +123,7 @@ extern void RelationCloseSmgrByOid(Oid relationId);
extern void AtEOXact_RelationCache(bool isCommit);
extern void AtEOSubXact_RelationCache(bool isCommit, SubTransactionId mySubid,
SubTransactionId parentSubid);
+extern void AtEOXact_DoPendingFlush(void);
/*
* Routines to help manage rebuilding of relcache init files
--
2.16.3
----Next_Part(Mon_May_20_15_54_31_2019_643)----
view thread (19+ messages) latest in thread
reply
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: [email protected]
Cc: [email protected]
Subject: Re: [PATCH 2/2] Fix WAL skipping feature
In-Reply-To: <no-message-id-215579@localhost>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox