Initial patch. I will be testing over next day. No commit before at
least midday on Wed 7 Apr.
The existing call to PrescanPreparedTransactions() looks correct to me
but the comment is wrong. I will change that also, if we agree.
--
Simon Riggs www.2ndQuadrant.com
diff --git a/src/backend/access/transam/twophase.c b/src/backend/access/transam/twophase.c
index e2566a4..365cd17 100644
--- a/src/backend/access/transam/twophase.c
+++ b/src/backend/access/transam/twophase.c
@@ -1719,6 +1719,88 @@ PrescanPreparedTransactions(TransactionId **xids_p, int *nxids_p)
}
/*
+ * StandbyRecoverPreparedTransactions
+ *
+ * Scan the pg_twophase directory and setup all the required information to
+ * allow standby queries to treat prepared transactions as still active.
+ * This is never called at the end of recovery - we use
+ * RecoverPreparedTransactions() at that point.
+ *
+ * Currently we simply call SubTransSetParent() for any subxids of prepared
+ * transactions.
+ */
+void
+StandbyRecoverPreparedTransactions(bool can_overwrite)
+{
+ DIR *cldir;
+ struct dirent *clde;
+
+ cldir = AllocateDir(TWOPHASE_DIR);
+ while ((clde = ReadDir(cldir, TWOPHASE_DIR)) != NULL)
+ {
+ if (strlen(clde->d_name) == 8 &&
+ strspn(clde->d_name, "0123456789ABCDEF") == 8)
+ {
+ TransactionId xid;
+ char *buf;
+ TwoPhaseFileHeader *hdr;
+ TransactionId *subxids;
+ int i;
+
+ xid = (TransactionId) strtoul(clde->d_name, NULL, 16);
+
+ /* Already processed? */
+ if (TransactionIdDidCommit(xid) || TransactionIdDidAbort(xid))
+ {
+ ereport(WARNING,
+ (errmsg("removing stale two-phase state file \"%s\"",
+ clde->d_name)));
+ RemoveTwoPhaseFile(xid, true);
+ continue;
+ }
+
+ /* Read and validate file */
+ buf = ReadTwoPhaseFile(xid, true);
+ if (buf == NULL)
+ {
+ ereport(WARNING,
+ (errmsg("removing corrupt two-phase state file \"%s\"",
+ clde->d_name)));
+ RemoveTwoPhaseFile(xid, true);
+ continue;
+ }
+
+ /* Deconstruct header */
+ hdr = (TwoPhaseFileHeader *) buf;
+ if (!TransactionIdEquals(hdr->xid, xid))
+ {
+ ereport(WARNING,
+ (errmsg("removing corrupt two-phase state file \"%s\"",
+ clde->d_name)));
+ RemoveTwoPhaseFile(xid, true);
+ pfree(buf);
+ continue;
+ }
+
+ /*
+ * Examine subtransaction XIDs ... they should all follow main
+ * XID, and they may force us to advance nextXid.
+ */
+ subxids = (TransactionId *)
+ (buf + MAXALIGN(sizeof(TwoPhaseFileHeader)));
+ for (i = 0; i < hdr->nsubxacts; i++)
+ {
+ TransactionId subxid = subxids[i];
+
+ Assert(TransactionIdFollows(subxid, xid));
+ SubTransSetParent(xid, subxid, can_overwrite);
+ }
+ }
+ }
+ FreeDir(cldir);
+}
+
+/*
* RecoverPreparedTransactions
*
* Scan the pg_twophase directory and reload shared-memory state for each
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index abdf4d8..08b4cf8 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5808,6 +5808,33 @@ StartupXLOG(void)
StartupMultiXact();
ProcArrayInitRecoveryInfo(oldestActiveXID);
+
+ /*
+ * If we're beginning at a shutdown checkpoint, we know that
+ * nothing was running on the master at this point. So fake-up
+ * an empty running-xacts record and use that here and now.
+ * Recover additional standby state for prepared transactions.
+ */
+ if (wasShutdown)
+ {
+ RunningTransactionsData running;
+
+ /*
+ * Construct a RunningTransactions snapshot representing a shut
+ * down server, with only prepared transactions still alive.
+ * We're never overflowed at this point because all subxids
+ * are listed with their parent prepared transactions.
+ */
+ running.xcnt = nxids;
+ running.subxid_overflow = false;
+ running.nextXid = checkPoint.nextXid;
+ running.oldestRunningXid = oldestActiveXID;
+ running.xids = xids;
+
+ ProcArrayApplyRecoveryInfo(&running);
+
+ StandbyRecoverPreparedTransactions(false);
+ }
}
/* Initialize resource managers */
@@ -7520,13 +7547,34 @@ xlog_redo(XLogRecPtr lsn, XLogRecord *record)
if (standbyState != STANDBY_DISABLED)
CheckRequiredParameterValues(checkPoint);
+ /*
+ * If we're beginning at a shutdown checkpoint, we know that
+ * nothing was running on the master at this point. So fake-up
+ * an empty running-xacts record and use that here and now.
+ * Recover additional standby state for prepared transactions.
+ */
if (standbyState >= STANDBY_INITIALIZED)
{
+ TransactionId *xids;
+ int nxids;
+ TransactionId oldestActiveXID = PrescanPreparedTransactions(&xids, &nxids);
+ RunningTransactionsData running;
+
/*
- * Remove stale transactions, if any.
+ * Construct a RunningTransactions snapshot representing a shut
+ * down server, with only prepared transactions still alive.
+ * We're never overflowed at this point because all subxids
+ * are listed with their parent prepared transactions.
*/
- ExpireOldKnownAssignedTransactionIds(checkPoint.nextXid);
- StandbyReleaseOldLocks(checkPoint.nextXid);
+ running.xcnt = nxids;
+ running.subxid_overflow = false;
+ running.nextXid = checkPoint.nextXid;
+ running.oldestRunningXid = oldestActiveXID;
+ running.xids = xids;
+
+ ProcArrayApplyRecoveryInfo(&running);
+
+ StandbyRecoverPreparedTransactions(true);
}
/* ControlFile->checkPointCopy always tracks the latest ckpt XID */
diff --git a/src/include/access/twophase.h b/src/include/access/twophase.h
index 5d9d6cf..46f5fca 100644
--- a/src/include/access/twophase.h
+++ b/src/include/access/twophase.h
@@ -44,6 +44,7 @@ extern bool StandbyTransactionIdIsPrepared(TransactionId xid);
extern TransactionId PrescanPreparedTransactions(TransactionId **xids_p,
int *nxids_p);
+extern void StandbyRecoverPreparedTransactions(bool can_overwrite);
extern void RecoverPreparedTransactions(void);
extern void RecreateTwoPhaseFile(TransactionId xid, void *content, int len);
--
Sent via pgsql-hackers mailing list (pgsql-hackers@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers
