postgresql/src/include/utils/snapshot.h

112 lines
3.8 KiB
C
Raw Normal View History

/*-------------------------------------------------------------------------
*
* snapshot.h
* POSTGRES snapshot definition
*
* Portions Copyright (c) 1996-2015, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
2010-09-20 22:08:53 +02:00
* src/include/utils/snapshot.h
*
*-------------------------------------------------------------------------
*/
#ifndef SNAPSHOT_H
#define SNAPSHOT_H
#include "access/htup.h"
#include "storage/buf.h"
typedef struct SnapshotData *Snapshot;
#define InvalidSnapshot ((Snapshot) NULL)
/*
* We use SnapshotData structures to represent both "regular" (MVCC)
* snapshots and "special" snapshots that have non-MVCC semantics.
* The specific semantics of a snapshot are encoded by the "satisfies"
* function.
*/
typedef bool (*SnapshotSatisfiesFunc) (HeapTuple htup,
Snapshot snapshot, Buffer buffer);
/*
* Struct representing all kind of possible snapshots.
*
* There are several different kinds of snapshots:
* * Normal MVCC snapshots
* * MVCC snapshots taken during recovery (in Hot-Standby mode)
* * Historic MVCC snapshots used during logical decoding
* * snapshots passed to HeapTupleSatisfiesDirty()
* * snapshots used for SatisfiesAny, Toast, Self where no members are
* accessed.
*
* TODO: It's probably a good idea to split this struct using a NodeTag
* similar to how parser and executor nodes are handled, with one type for
* each different kind of snapshot to avoid overloading the meaning of
* individual fields.
*/
typedef struct SnapshotData
{
SnapshotSatisfiesFunc satisfies; /* tuple test function */
/*
* The remaining fields are used only for MVCC snapshots, and are normally
* just zeroes in special snapshots. (But xmin and xmax are used
* specially by HeapTupleSatisfiesDirty.)
*
* An MVCC snapshot can never see the effects of XIDs >= xmax. It can see
* the effects of all older XIDs except those listed in the snapshot. xmin
* is stored as an optimization to avoid needing to search the XID arrays
* for most tuples.
*/
TransactionId xmin; /* all XID < xmin are visible to me */
TransactionId xmax; /* all XID >= xmax are invisible to me */
/*
* For normal MVCC snapshot this contains the all xact IDs that are in
* progress, unless the snapshot was taken during recovery in which case
* it's empty. For historic MVCC snapshots, the meaning is inverted, i.e.
* it contains *committed* transactions between xmin and xmax.
*/
TransactionId *xip;
uint32 xcnt; /* # of xact ids in xip[] */
/* note: all ids in xip[] satisfy xmin <= xip[i] < xmax */
Allow read only connections during recovery, known as Hot Standby. Enabled by recovery_connections = on (default) and forcing archive recovery using a recovery.conf. Recovery processing now emulates the original transactions as they are replayed, providing full locking and MVCC behaviour for read only queries. Recovery must enter consistent state before connections are allowed, so there is a delay, typically short, before connections succeed. Replay of recovering transactions can conflict and in some cases deadlock with queries during recovery; these result in query cancellation after max_standby_delay seconds have expired. Infrastructure changes have minor effects on normal running, though introduce four new types of WAL record. New test mode "make standbycheck" allows regression tests of static command behaviour on a standby server while in recovery. Typical and extreme dynamic behaviours have been checked via code inspection and manual testing. Few port specific behaviours have been utilised, though primary testing has been on Linux only so far. This commit is the basic patch. Additional changes will follow in this release to enhance some aspects of behaviour, notably improved handling of conflicts, deadlock detection and query cancellation. Changes to VACUUM FULL are also required. Simon Riggs, with significant and lengthy review by Heikki Linnakangas, including streamlined redesign of snapshot creation and two-phase commit. Important contributions from Florian Pflug, Mark Kirkwood, Merlin Moncure, Greg Stark, Gianni Ciolli, Gabriele Bartolini, Hannu Krosing, Robert Haas, Tatsuo Ishii, Hiroyuki Yamada plus support and feedback from many other community members.
2009-12-19 02:32:45 +01:00
int32 subxcnt; /* # of xact ids in subxip[] */
/*
* For non-historic MVCC snapshots, this contains subxact IDs that are in
* progress (and other transactions that are in progress if taken during
* recovery). For historic snapshot it contains *all* xids assigned to the
* replayed transaction, including the toplevel xid.
*/
TransactionId *subxip;
Allow read only connections during recovery, known as Hot Standby. Enabled by recovery_connections = on (default) and forcing archive recovery using a recovery.conf. Recovery processing now emulates the original transactions as they are replayed, providing full locking and MVCC behaviour for read only queries. Recovery must enter consistent state before connections are allowed, so there is a delay, typically short, before connections succeed. Replay of recovering transactions can conflict and in some cases deadlock with queries during recovery; these result in query cancellation after max_standby_delay seconds have expired. Infrastructure changes have minor effects on normal running, though introduce four new types of WAL record. New test mode "make standbycheck" allows regression tests of static command behaviour on a standby server while in recovery. Typical and extreme dynamic behaviours have been checked via code inspection and manual testing. Few port specific behaviours have been utilised, though primary testing has been on Linux only so far. This commit is the basic patch. Additional changes will follow in this release to enhance some aspects of behaviour, notably improved handling of conflicts, deadlock detection and query cancellation. Changes to VACUUM FULL are also required. Simon Riggs, with significant and lengthy review by Heikki Linnakangas, including streamlined redesign of snapshot creation and two-phase commit. Important contributions from Florian Pflug, Mark Kirkwood, Merlin Moncure, Greg Stark, Gianni Ciolli, Gabriele Bartolini, Hannu Krosing, Robert Haas, Tatsuo Ishii, Hiroyuki Yamada plus support and feedback from many other community members.
2009-12-19 02:32:45 +01:00
bool suboverflowed; /* has the subxip array overflowed? */
bool takenDuringRecovery; /* recovery-shaped snapshot? */
bool copied; /* false if it's a static snapshot */
/*
* note: all ids in subxip[] are >= xmin, but we don't bother filtering
* out any that are >= xmax
*/
CommandId curcid; /* in my xact, CID < curcid are visible */
uint32 active_count; /* refcount on ActiveSnapshot stack */
uint32 regd_count; /* refcount on RegisteredSnapshotList */
} SnapshotData;
/*
* Result codes for HeapTupleSatisfiesUpdate. This should really be in
* tqual.h, but we want to avoid including that file elsewhere.
*/
typedef enum
{
HeapTupleMayBeUpdated,
HeapTupleInvisible,
HeapTupleSelfUpdated,
HeapTupleUpdated,
HeapTupleBeingUpdated,
HeapTupleWouldBlock /* can be returned by heap_tuple_lock */
} HTSU_Result;
#endif /* SNAPSHOT_H */