postgresql/src/include/access/commit_ts.h
Alvaro Herrera 8eace46d34 Fix race condition in reading commit timestamps
If a user requests the commit timestamp for a transaction old enough
that its data is concurrently being truncated away by vacuum at just the
right time, they would receive an ugly internal file-not-found error
message from slru.c rather than the expected NULL return value.

In a primary server, the window for the race is very small: the lookup
has to occur exactly between the two calls by vacuum, and there's not a
lot that happens between them (mostly just a multixact truncate).  In a
standby server, however, the window is larger because the truncation is
executed as soon as the WAL record for it is replayed, but the advance
of the oldest-Xid is not executed until the next checkpoint record.

To fix in the primary, simply reverse the order of operations in
vac_truncate_clog.  To fix in the standby, augment the WAL truncation
record so that the standby is aware of the new oldest-XID value and can
apply the update immediately.  WAL version bumped because of this.

No backpatch, because of the low importance of the bug and its rarity.

Author: Craig Ringer
Reviewed-By: Petr Jelínek, Peter Eisentraut
Discussion: https://postgr.es/m/CAMsr+YFhVtRQT1VAwC+WGbbxZZRzNou=N9Ed-FrCqkwQ8H8oJQ@mail.gmail.com
2017-01-19 18:24:17 -03:00

77 lines
2.3 KiB
C

/*
* commit_ts.h
*
* PostgreSQL commit timestamp manager
*
* Portions Copyright (c) 1996-2017, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* src/include/access/commit_ts.h
*/
#ifndef COMMIT_TS_H
#define COMMIT_TS_H
#include "access/xlog.h"
#include "datatype/timestamp.h"
#include "replication/origin.h"
#include "utils/guc.h"
extern PGDLLIMPORT bool track_commit_timestamp;
extern bool check_track_commit_timestamp(bool *newval, void **extra,
GucSource source);
extern void TransactionTreeSetCommitTsData(TransactionId xid, int nsubxids,
TransactionId *subxids, TimestampTz timestamp,
RepOriginId nodeid, bool write_xlog);
extern bool TransactionIdGetCommitTsData(TransactionId xid,
TimestampTz *ts, RepOriginId *nodeid);
extern TransactionId GetLatestCommitTsData(TimestampTz *ts,
RepOriginId *nodeid);
extern Size CommitTsShmemBuffers(void);
extern Size CommitTsShmemSize(void);
extern void CommitTsShmemInit(void);
extern void BootStrapCommitTs(void);
extern void StartupCommitTs(void);
extern void CommitTsParameterChange(bool xlrecvalue, bool pgcontrolvalue);
extern void CompleteCommitTsInitialization(void);
extern void ShutdownCommitTs(void);
extern void CheckPointCommitTs(void);
extern void ExtendCommitTs(TransactionId newestXact);
extern void TruncateCommitTs(TransactionId oldestXact);
extern void SetCommitTsLimit(TransactionId oldestXact,
TransactionId newestXact);
extern void AdvanceOldestCommitTsXid(TransactionId oldestXact);
/* XLOG stuff */
#define COMMIT_TS_ZEROPAGE 0x00
#define COMMIT_TS_TRUNCATE 0x10
#define COMMIT_TS_SETTS 0x20
typedef struct xl_commit_ts_set
{
TimestampTz timestamp;
RepOriginId nodeid;
TransactionId mainxid;
/* subxact Xids follow */
} xl_commit_ts_set;
#define SizeOfCommitTsSet (offsetof(xl_commit_ts_set, mainxid) + \
sizeof(TransactionId))
typedef struct xl_commit_ts_truncate
{
int pageno;
TransactionId oldestXid;
} xl_commit_ts_truncate;
#define SizeOfCommitTsTruncate (offsetof(xl_commit_ts_truncate, oldestXid) + \
sizeof(TransactionId))
extern void commit_ts_redo(XLogReaderState *record);
extern void commit_ts_desc(StringInfo buf, XLogReaderState *record);
extern const char *commit_ts_identify(uint8 info);
#endif /* COMMIT_TS_H */