When wal_level=logical, write invalidations at command end into WAL so
that decoding can use this information.
This patch is required to allow the streaming of in-progress transactions
in logical decoding. The actual work to allow streaming will be committed
as a separate patch.
We still add the invalidations to the cache and write them to WAL at
commit time in RecordTransactionCommit(). This uses the existing
XLOG_INVALIDATIONS xlog record type, from the RM_STANDBY_ID resource
manager (see LogStandbyInvalidations for details).
So existing code relying on those invalidations (e.g. redo) does not need
to be changed.
The invalidations written at command end uses a new xlog record type
XLOG_XACT_INVALIDATIONS, from RM_XACT_ID resource manager. See
LogLogicalInvalidations for details.
These new xlog records are ignored by existing redo procedures, which
still rely on the invalidations written to commit records.
The invalidations are decoded and accumulated in top-transaction, and then
executed during replay. This obviates the need to decode the
invalidations as part of a commit record.
Bump XLOG_PAGE_MAGIC, since this introduces XLOG_XACT_INVALIDATIONS.
Author: Dilip Kumar, Tomas Vondra, Amit Kapila
Reviewed-by: Amit Kapila
Tested-by: Neha Sharma and Mahendra Singh Thalor
Discussion: https://postgr.es/m/
688b0b7f-2f6c-d827-c27b-
216a8e3ea700@2ndquadrant.com
appendStringInfo(buf, "xtop %u: ", xlrec->xtop);
xact_desc_assignment(buf, xlrec);
}
+ else if (info == XLOG_XACT_INVALIDATIONS)
+ {
+ xl_xact_invals *xlrec = (xl_xact_invals *) rec;
+
+ standby_desc_invalidations(buf, xlrec->nmsgs, xlrec->msgs, InvalidOid,
+ InvalidOid, false);
+ }
}
const char *
case XLOG_XACT_ASSIGNMENT:
id = "ASSIGNMENT";
break;
+ case XLOG_XACT_INVALIDATIONS:
+ id = "INVALIDATION";
+ break;
}
return id;
bool RelcacheInitFileInval = false;
bool wrote_xlog;
+ /*
+ * Log pending invalidations for logical decoding of in-progress
+ * transactions. Normally for DDLs, we log this at each command end,
+ * however, for certain cases where we directly update the system table
+ * without a transaction block, the invalidations are not logged till this
+ * time.
+ */
+ if (XLogLogicalInfoActive())
+ LogLogicalInvalidations();
+
/* Get data needed for commit record */
nrels = smgrGetPendingDeletes(true, &rels);
nchildren = xactGetCommittedChildren(&children);
ProcArrayApplyXidAssignment(xlrec->xtop,
xlrec->nsubxacts, xlrec->xsub);
}
+ else if (info == XLOG_XACT_INVALIDATIONS)
+ {
+ /*
+ * XXX we do ignore this for now, what matters are invalidations
+ * written into the commit record.
+ */
+ }
else
elog(PANIC, "xact_redo: unknown op code %u", info);
}
/*
* We assign subxact to the toplevel xact while processing each
- * record if required. So, we don't need to do anything here.
- * See LogicalDecodingProcessRecord.
+ * record if required. So, we don't need to do anything here. See
+ * LogicalDecodingProcessRecord.
*/
break;
+ case XLOG_XACT_INVALIDATIONS:
+ {
+ TransactionId xid;
+ xl_xact_invals *invals;
+
+ xid = XLogRecGetXid(r);
+ invals = (xl_xact_invals *) XLogRecGetData(r);
+
+ /*
+ * Execute the invalidations for xid-less transactions,
+ * otherwise, accumulate them so that they can be processed at
+ * the commit time.
+ */
+ if (TransactionIdIsValid(xid))
+ {
+ if (!ctx->fast_forward)
+ ReorderBufferAddInvalidations(reorder, xid,
+ buf->origptr,
+ invals->nmsgs,
+ invals->msgs);
+ ReorderBufferXidSetCatalogChanges(ctx->reorder, xid,
+ buf->origptr);
+ }
+ else if ((!ctx->fast_forward))
+ ReorderBufferImmediateInvalidation(ctx->reorder,
+ invals->nmsgs,
+ invals->msgs);
+ }
+ break;
case XLOG_XACT_PREPARE:
/*
case XLOG_STANDBY_LOCK:
break;
case XLOG_INVALIDATIONS:
- {
- xl_invalidations *invalidations =
- (xl_invalidations *) XLogRecGetData(r);
- if (!ctx->fast_forward)
- ReorderBufferImmediateInvalidation(ctx->reorder,
- invalidations->nmsgs,
- invalidations->msgs);
- }
+ /*
+ * We are processing the invalidations at the command level via
+ * XLOG_XACT_INVALIDATIONS. So we don't need to do anything here.
+ */
break;
default:
elog(ERROR, "unexpected RM_STANDBY_ID record type: %u", info);
commit_time = parsed->origin_timestamp;
}
- /*
- * Process invalidation messages, even if we're not interested in the
- * transaction's contents, since the various caches need to always be
- * consistent.
- */
- if (parsed->nmsgs > 0)
- {
- if (!ctx->fast_forward)
- ReorderBufferAddInvalidations(ctx->reorder, xid, buf->origptr,
- parsed->nmsgs, parsed->msgs);
- ReorderBufferXidSetCatalogChanges(ctx->reorder, xid, buf->origptr);
- }
-
SnapBuildCommitTxn(ctx->snapshot_builder, buf->origptr, xid,
parsed->nsubxacts, parsed->subxacts);
subtxn->toplevel_xid = xid;
Assert(subtxn->nsubtxns == 0);
+ /* set the reference to top-level transaction */
+ subtxn->toptxn = txn;
+
/* add to subtransaction list */
dlist_push_tail(&txn->subtxns, &subtxn->node);
txn->nsubtxns++;
/*
* Setup the invalidation of the toplevel transaction.
*
- * This needs to be done before ReorderBufferCommit is called!
+ * This needs to be called for each XLOG_XACT_INVALIDATIONS message and
+ * accumulates all the invalidation messages in the toplevel transaction.
+ * This is required because in some cases where we skip processing the
+ * transaction (see ReorderBufferForget), we need to execute all the
+ * invalidations together.
*/
void
ReorderBufferAddInvalidations(ReorderBuffer *rb, TransactionId xid,
txn = ReorderBufferTXNByXid(rb, xid, true, NULL, lsn, true);
- if (txn->ninvalidations != 0)
- elog(ERROR, "only ever add one set of invalidations");
+ /*
+ * We collect all the invalidations under the top transaction so that we
+ * can execute them all together.
+ */
+ if (txn->toptxn)
+ txn = txn->toptxn;
Assert(nmsgs > 0);
- txn->ninvalidations = nmsgs;
- txn->invalidations = (SharedInvalidationMessage *)
- MemoryContextAlloc(rb->context,
- sizeof(SharedInvalidationMessage) * nmsgs);
- memcpy(txn->invalidations, msgs,
- sizeof(SharedInvalidationMessage) * nmsgs);
+ /* Accumulate invalidations. */
+ if (txn->ninvalidations == 0)
+ {
+ txn->ninvalidations = nmsgs;
+ txn->invalidations = (SharedInvalidationMessage *)
+ MemoryContextAlloc(rb->context,
+ sizeof(SharedInvalidationMessage) * nmsgs);
+ memcpy(txn->invalidations, msgs,
+ sizeof(SharedInvalidationMessage) * nmsgs);
+ }
+ else
+ {
+ txn->invalidations = (SharedInvalidationMessage *)
+ repalloc(txn->invalidations, sizeof(SharedInvalidationMessage) *
+ (txn->ninvalidations + nmsgs));
+
+ memcpy(txn->invalidations + txn->ninvalidations, msgs,
+ nmsgs * sizeof(SharedInvalidationMessage));
+ txn->ninvalidations += nmsgs;
+ }
}
/*
txn = ReorderBufferTXNByXid(rb, xid, true, NULL, lsn, true);
txn->txn_flags |= RBTXN_HAS_CATALOG_CHANGES;
+
+ /*
+ * Mark top-level transaction as having catalog changes too if one of its
+ * children has so that the ReorderBufferBuildTupleCidHash can
+ * conveniently check just top-level transaction and decide whether to
+ * build the hash table or not.
+ */
+ if (txn->toptxn != NULL)
+ txn->toptxn->txn_flags |= RBTXN_HAS_CATALOG_CHANGES;
}
/*
* worth trying to avoid sending such inval traffic in the future, if those
* problems can be overcome cheaply.
*
+ * When wal_level=logical, write invalidations into WAL at each command end to
+ * support the decoding of the in-progress transactions. See
+ * CommandEndInvalidationMessages.
*
* Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
ProcessInvalidationMessages(&transInvalInfo->CurrentCmdInvalidMsgs,
LocalExecuteInvalidationMessage);
+
+ /* WAL Log per-command invalidation messages for wal_level=logical */
+ if (XLogLogicalInfoActive())
+ LogLogicalInvalidations();
+
AppendInvalidationMessages(&transInvalInfo->PriorCmdInvalidMsgs,
&transInvalInfo->CurrentCmdInvalidMsgs);
}
i = ccitem->link - 1;
}
}
+
+/*
+ * LogLogicalInvalidations
+ *
+ * Emit WAL for invalidations. This is currently only used for logging
+ * invalidations at the command end or at commit time if any invalidations
+ * are pending.
+ */
+void
+LogLogicalInvalidations()
+{
+ xl_xact_invals xlrec;
+ SharedInvalidationMessage *invalMessages;
+ int nmsgs = 0;
+
+ /* Quick exit if we haven't done anything with invalidation messages. */
+ if (transInvalInfo == NULL)
+ return;
+
+ ProcessInvalidationMessagesMulti(&transInvalInfo->CurrentCmdInvalidMsgs,
+ MakeSharedInvalidMessagesArray);
+
+ Assert(!(numSharedInvalidMessagesArray > 0 &&
+ SharedInvalidMessagesArray == NULL));
+
+ invalMessages = SharedInvalidMessagesArray;
+ nmsgs = numSharedInvalidMessagesArray;
+ SharedInvalidMessagesArray = NULL;
+ numSharedInvalidMessagesArray = 0;
+
+ if (nmsgs > 0)
+ {
+ /* prepare record */
+ memset(&xlrec, 0, MinSizeOfXactInvals);
+ xlrec.nmsgs = nmsgs;
+
+ /* perform insertion */
+ XLogBeginInsert();
+ XLogRegisterData((char *) (&xlrec), MinSizeOfXactInvals);
+ XLogRegisterData((char *) invalMessages,
+ nmsgs * sizeof(SharedInvalidationMessage));
+ XLogInsert(RM_XACT_ID, XLOG_XACT_INVALIDATIONS);
+
+ pfree(invalMessages);
+ }
+}
#define XLOG_XACT_COMMIT_PREPARED 0x30
#define XLOG_XACT_ABORT_PREPARED 0x40
#define XLOG_XACT_ASSIGNMENT 0x50
-/* free opcode 0x60 */
+#define XLOG_XACT_INVALIDATIONS 0x60
/* free opcode 0x70 */
/* mask for filtering opcodes out of xl_info */
/*
* Each page of XLOG file has a header like this:
*/
-#define XLOG_PAGE_MAGIC 0xD107 /* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD108 /* can be used as WAL version indicator */
typedef struct XLogPageHeaderData
{
*/
XLogRecPtr end_lsn;
+ /* Toplevel transaction for this subxact (NULL for top-level). */
+ struct ReorderBufferTXN *toptxn;
+
/*
* LSN of the last lsn at which snapshot information reside, so we can
* restart decoding from there and fully recover this transaction from
extern void CallSyscacheCallbacks(int cacheid, uint32 hashvalue);
extern void InvalidateSystemCaches(void);
+
+extern void LogLogicalInvalidations(void);
#endif /* INVAL_H */
projects / postgresql.git / commitdiff