2000-10-28 18:21:00 +02:00
|
|
|
/*
|
|
|
|
|
* xlogdefs.h
|
|
|
|
|
*
|
|
|
|
|
* Postgres transaction log manager record pointer and
|
2004-07-22 00:31:26 +02:00
|
|
|
* timeline number definitions
|
XLOG (and related) changes:
* Store two past checkpoint locations, not just one, in pg_control.
On startup, we fall back to the older checkpoint if the newer one
is unreadable. Also, a physical copy of the newest checkpoint record
is kept in pg_control for possible use in disaster recovery (ie,
complete loss of pg_xlog). Also add a version number for pg_control
itself. Remove archdir from pg_control; it ought to be a GUC
parameter, not a special case (not that it's implemented yet anyway).
* Suppress successive checkpoint records when nothing has been entered
in the WAL log since the last one. This is not so much to avoid I/O
as to make it actually useful to keep track of the last two
checkpoints. If the things are right next to each other then there's
not a lot of redundancy gained...
* Change CRC scheme to a true 64-bit CRC, not a pair of 32-bit CRCs
on alternate bytes. Polynomial borrowed from ECMA DLT1 standard.
* Fix XLOG record length handling so that it will work at BLCKSZ = 32k.
* Change XID allocation to work more like OID allocation. (This is of
dubious necessity, but I think it's a good idea anyway.)
* Fix a number of minor bugs, such as off-by-one logic for XLOG file
wraparound at the 4 gig mark.
* Add documentation and clean up some coding infelicities; move file
format declarations out to include files where planned contrib
utilities can get at them.
* Checkpoint will now occur every CHECKPOINT_SEGMENTS log segments or
every CHECKPOINT_TIMEOUT seconds, whichever comes first. It is also
possible to force a checkpoint by sending SIGUSR1 to the postmaster
(undocumented feature...)
* Defend against kill -9 postmaster by storing shmem block's key and ID
in postmaster.pid lockfile, and checking at startup to ensure that no
processes are still connected to old shmem block (if it still exists).
* Switch backends to accept SIGQUIT rather than SIGUSR1 for emergency
stop, for symmetry with postmaster and xlog utilities. Clean up signal
handling in bootstrap.c so that xlog utilities launched by postmaster
will react to signals better.
* Standalone bootstrap now grabs lockfile in target directory, as added
insurance against running it in parallel with live postmaster.
2001-03-13 02:17:06 +01:00
|
|
|
*
|
2007-01-05 23:20:05 +01:00
|
|
|
* Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
|
XLOG (and related) changes:
* Store two past checkpoint locations, not just one, in pg_control.
On startup, we fall back to the older checkpoint if the newer one
is unreadable. Also, a physical copy of the newest checkpoint record
is kept in pg_control for possible use in disaster recovery (ie,
complete loss of pg_xlog). Also add a version number for pg_control
itself. Remove archdir from pg_control; it ought to be a GUC
parameter, not a special case (not that it's implemented yet anyway).
* Suppress successive checkpoint records when nothing has been entered
in the WAL log since the last one. This is not so much to avoid I/O
as to make it actually useful to keep track of the last two
checkpoints. If the things are right next to each other then there's
not a lot of redundancy gained...
* Change CRC scheme to a true 64-bit CRC, not a pair of 32-bit CRCs
on alternate bytes. Polynomial borrowed from ECMA DLT1 standard.
* Fix XLOG record length handling so that it will work at BLCKSZ = 32k.
* Change XID allocation to work more like OID allocation. (This is of
dubious necessity, but I think it's a good idea anyway.)
* Fix a number of minor bugs, such as off-by-one logic for XLOG file
wraparound at the 4 gig mark.
* Add documentation and clean up some coding infelicities; move file
format declarations out to include files where planned contrib
utilities can get at them.
* Checkpoint will now occur every CHECKPOINT_SEGMENTS log segments or
every CHECKPOINT_TIMEOUT seconds, whichever comes first. It is also
possible to force a checkpoint by sending SIGUSR1 to the postmaster
(undocumented feature...)
* Defend against kill -9 postmaster by storing shmem block's key and ID
in postmaster.pid lockfile, and checking at startup to ensure that no
processes are still connected to old shmem block (if it still exists).
* Switch backends to accept SIGQUIT rather than SIGUSR1 for emergency
stop, for symmetry with postmaster and xlog utilities. Clean up signal
handling in bootstrap.c so that xlog utilities launched by postmaster
will react to signals better.
* Standalone bootstrap now grabs lockfile in target directory, as added
insurance against running it in parallel with live postmaster.
2001-03-13 02:17:06 +01:00
|
|
|
* Portions Copyright (c) 1994, Regents of the University of California
|
2000-10-28 18:21:00 +02:00
|
|
|
*
|
2007-02-14 06:00:40 +01:00
|
|
|
* $PostgreSQL: pgsql/src/include/access/xlogdefs.h,v 1.17 2007/02/14 05:00:40 momjian Exp $
|
2000-10-28 18:21:00 +02:00
|
|
|
*/
|
|
|
|
|
#ifndef XLOG_DEFS_H
|
|
|
|
|
#define XLOG_DEFS_H
|
|
|
|
|
|
XLOG (and related) changes:
* Store two past checkpoint locations, not just one, in pg_control.
On startup, we fall back to the older checkpoint if the newer one
is unreadable. Also, a physical copy of the newest checkpoint record
is kept in pg_control for possible use in disaster recovery (ie,
complete loss of pg_xlog). Also add a version number for pg_control
itself. Remove archdir from pg_control; it ought to be a GUC
parameter, not a special case (not that it's implemented yet anyway).
* Suppress successive checkpoint records when nothing has been entered
in the WAL log since the last one. This is not so much to avoid I/O
as to make it actually useful to keep track of the last two
checkpoints. If the things are right next to each other then there's
not a lot of redundancy gained...
* Change CRC scheme to a true 64-bit CRC, not a pair of 32-bit CRCs
on alternate bytes. Polynomial borrowed from ECMA DLT1 standard.
* Fix XLOG record length handling so that it will work at BLCKSZ = 32k.
* Change XID allocation to work more like OID allocation. (This is of
dubious necessity, but I think it's a good idea anyway.)
* Fix a number of minor bugs, such as off-by-one logic for XLOG file
wraparound at the 4 gig mark.
* Add documentation and clean up some coding infelicities; move file
format declarations out to include files where planned contrib
utilities can get at them.
* Checkpoint will now occur every CHECKPOINT_SEGMENTS log segments or
every CHECKPOINT_TIMEOUT seconds, whichever comes first. It is also
possible to force a checkpoint by sending SIGUSR1 to the postmaster
(undocumented feature...)
* Defend against kill -9 postmaster by storing shmem block's key and ID
in postmaster.pid lockfile, and checking at startup to ensure that no
processes are still connected to old shmem block (if it still exists).
* Switch backends to accept SIGQUIT rather than SIGUSR1 for emergency
stop, for symmetry with postmaster and xlog utilities. Clean up signal
handling in bootstrap.c so that xlog utilities launched by postmaster
will react to signals better.
* Standalone bootstrap now grabs lockfile in target directory, as added
insurance against running it in parallel with live postmaster.
2001-03-13 02:17:06 +01:00
|
|
|
/*
|
|
|
|
|
* Pointer to a location in the XLOG. These pointers are 64 bits wide,
|
|
|
|
|
* because we don't want them ever to overflow.
|
|
|
|
|
*
|
|
|
|
|
* NOTE: xrecoff == 0 is used to indicate an invalid pointer. This is OK
|
|
|
|
|
* because we use page headers in the XLOG, so no XLOG record can start
|
|
|
|
|
* right at the beginning of a file.
|
|
|
|
|
*
|
|
|
|
|
* NOTE: the "log file number" is somewhat misnamed, since the actual files
|
|
|
|
|
* making up the XLOG are much smaller than 4Gb. Each actual file is an
|
|
|
|
|
* XLogSegSize-byte "segment" of a logical log file having the indicated
|
2001-03-22 05:01:46 +01:00
|
|
|
* xlogid. The log file number and segment number together identify a
|
|
|
|
|
* physical XLOG file. Segment number and offset within the physical file
|
XLOG (and related) changes:
* Store two past checkpoint locations, not just one, in pg_control.
On startup, we fall back to the older checkpoint if the newer one
is unreadable. Also, a physical copy of the newest checkpoint record
is kept in pg_control for possible use in disaster recovery (ie,
complete loss of pg_xlog). Also add a version number for pg_control
itself. Remove archdir from pg_control; it ought to be a GUC
parameter, not a special case (not that it's implemented yet anyway).
* Suppress successive checkpoint records when nothing has been entered
in the WAL log since the last one. This is not so much to avoid I/O
as to make it actually useful to keep track of the last two
checkpoints. If the things are right next to each other then there's
not a lot of redundancy gained...
* Change CRC scheme to a true 64-bit CRC, not a pair of 32-bit CRCs
on alternate bytes. Polynomial borrowed from ECMA DLT1 standard.
* Fix XLOG record length handling so that it will work at BLCKSZ = 32k.
* Change XID allocation to work more like OID allocation. (This is of
dubious necessity, but I think it's a good idea anyway.)
* Fix a number of minor bugs, such as off-by-one logic for XLOG file
wraparound at the 4 gig mark.
* Add documentation and clean up some coding infelicities; move file
format declarations out to include files where planned contrib
utilities can get at them.
* Checkpoint will now occur every CHECKPOINT_SEGMENTS log segments or
every CHECKPOINT_TIMEOUT seconds, whichever comes first. It is also
possible to force a checkpoint by sending SIGUSR1 to the postmaster
(undocumented feature...)
* Defend against kill -9 postmaster by storing shmem block's key and ID
in postmaster.pid lockfile, and checking at startup to ensure that no
processes are still connected to old shmem block (if it still exists).
* Switch backends to accept SIGQUIT rather than SIGUSR1 for emergency
stop, for symmetry with postmaster and xlog utilities. Clean up signal
handling in bootstrap.c so that xlog utilities launched by postmaster
will react to signals better.
* Standalone bootstrap now grabs lockfile in target directory, as added
insurance against running it in parallel with live postmaster.
2001-03-13 02:17:06 +01:00
|
|
|
* are computed from xrecoff div and mod XLogSegSize.
|
|
|
|
|
*/
|
2000-10-28 18:21:00 +02:00
|
|
|
typedef struct XLogRecPtr
|
|
|
|
|
{
|
|
|
|
|
uint32 xlogid; /* log file #, 0 based */
|
XLOG (and related) changes:
* Store two past checkpoint locations, not just one, in pg_control.
On startup, we fall back to the older checkpoint if the newer one
is unreadable. Also, a physical copy of the newest checkpoint record
is kept in pg_control for possible use in disaster recovery (ie,
complete loss of pg_xlog). Also add a version number for pg_control
itself. Remove archdir from pg_control; it ought to be a GUC
parameter, not a special case (not that it's implemented yet anyway).
* Suppress successive checkpoint records when nothing has been entered
in the WAL log since the last one. This is not so much to avoid I/O
as to make it actually useful to keep track of the last two
checkpoints. If the things are right next to each other then there's
not a lot of redundancy gained...
* Change CRC scheme to a true 64-bit CRC, not a pair of 32-bit CRCs
on alternate bytes. Polynomial borrowed from ECMA DLT1 standard.
* Fix XLOG record length handling so that it will work at BLCKSZ = 32k.
* Change XID allocation to work more like OID allocation. (This is of
dubious necessity, but I think it's a good idea anyway.)
* Fix a number of minor bugs, such as off-by-one logic for XLOG file
wraparound at the 4 gig mark.
* Add documentation and clean up some coding infelicities; move file
format declarations out to include files where planned contrib
utilities can get at them.
* Checkpoint will now occur every CHECKPOINT_SEGMENTS log segments or
every CHECKPOINT_TIMEOUT seconds, whichever comes first. It is also
possible to force a checkpoint by sending SIGUSR1 to the postmaster
(undocumented feature...)
* Defend against kill -9 postmaster by storing shmem block's key and ID
in postmaster.pid lockfile, and checking at startup to ensure that no
processes are still connected to old shmem block (if it still exists).
* Switch backends to accept SIGQUIT rather than SIGUSR1 for emergency
stop, for symmetry with postmaster and xlog utilities. Clean up signal
handling in bootstrap.c so that xlog utilities launched by postmaster
will react to signals better.
* Standalone bootstrap now grabs lockfile in target directory, as added
insurance against running it in parallel with live postmaster.
2001-03-13 02:17:06 +01:00
|
|
|
uint32 xrecoff; /* byte offset of location in log file */
|
2000-10-28 18:21:00 +02:00
|
|
|
} XLogRecPtr;
|
|
|
|
|
|
2003-12-20 18:31:21 +01:00
|
|
|
|
XLOG (and related) changes:
* Store two past checkpoint locations, not just one, in pg_control.
On startup, we fall back to the older checkpoint if the newer one
is unreadable. Also, a physical copy of the newest checkpoint record
is kept in pg_control for possible use in disaster recovery (ie,
complete loss of pg_xlog). Also add a version number for pg_control
itself. Remove archdir from pg_control; it ought to be a GUC
parameter, not a special case (not that it's implemented yet anyway).
* Suppress successive checkpoint records when nothing has been entered
in the WAL log since the last one. This is not so much to avoid I/O
as to make it actually useful to keep track of the last two
checkpoints. If the things are right next to each other then there's
not a lot of redundancy gained...
* Change CRC scheme to a true 64-bit CRC, not a pair of 32-bit CRCs
on alternate bytes. Polynomial borrowed from ECMA DLT1 standard.
* Fix XLOG record length handling so that it will work at BLCKSZ = 32k.
* Change XID allocation to work more like OID allocation. (This is of
dubious necessity, but I think it's a good idea anyway.)
* Fix a number of minor bugs, such as off-by-one logic for XLOG file
wraparound at the 4 gig mark.
* Add documentation and clean up some coding infelicities; move file
format declarations out to include files where planned contrib
utilities can get at them.
* Checkpoint will now occur every CHECKPOINT_SEGMENTS log segments or
every CHECKPOINT_TIMEOUT seconds, whichever comes first. It is also
possible to force a checkpoint by sending SIGUSR1 to the postmaster
(undocumented feature...)
* Defend against kill -9 postmaster by storing shmem block's key and ID
in postmaster.pid lockfile, and checking at startup to ensure that no
processes are still connected to old shmem block (if it still exists).
* Switch backends to accept SIGQUIT rather than SIGUSR1 for emergency
stop, for symmetry with postmaster and xlog utilities. Clean up signal
handling in bootstrap.c so that xlog utilities launched by postmaster
will react to signals better.
* Standalone bootstrap now grabs lockfile in target directory, as added
insurance against running it in parallel with live postmaster.
2001-03-13 02:17:06 +01:00
|
|
|
/*
|
|
|
|
|
* Macros for comparing XLogRecPtrs
|
|
|
|
|
*
|
|
|
|
|
* Beware of passing expressions with side-effects to these macros,
|
|
|
|
|
* since the arguments may be evaluated multiple times.
|
|
|
|
|
*/
|
|
|
|
|
#define XLByteLT(a, b) \
|
|
|
|
|
((a).xlogid < (b).xlogid || \
|
|
|
|
|
((a).xlogid == (b).xlogid && (a).xrecoff < (b).xrecoff))
|
|
|
|
|
|
|
|
|
|
#define XLByteLE(a, b) \
|
|
|
|
|
((a).xlogid < (b).xlogid || \
|
|
|
|
|
((a).xlogid == (b).xlogid && (a).xrecoff <= (b).xrecoff))
|
|
|
|
|
|
|
|
|
|
#define XLByteEQ(a, b) \
|
|
|
|
|
((a).xlogid == (b).xlogid && (a).xrecoff == (b).xrecoff)
|
|
|
|
|
|
2004-07-22 00:31:26 +02:00
|
|
|
|
2000-10-28 18:21:00 +02:00
|
|
|
/*
|
2004-07-22 00:31:26 +02:00
|
|
|
* TimeLineID (TLI) - identifies different database histories to prevent
|
|
|
|
|
* confusion after restoring a prior state of a database installation.
|
|
|
|
|
* TLI does not change in a normal stop/restart of the database (including
|
|
|
|
|
* crash-and-recover cases); but we must assign a new TLI after doing
|
|
|
|
|
* a recovery to a prior state, a/k/a point-in-time recovery. This makes
|
|
|
|
|
* the new WAL logfile sequence we generate distinguishable from the
|
|
|
|
|
* sequence that was generated in the previous incarnation.
|
2000-10-28 18:21:00 +02:00
|
|
|
*/
|
2004-07-22 00:31:26 +02:00
|
|
|
typedef uint32 TimeLineID;
|
2001-10-28 07:26:15 +01:00
|
|
|
|
2007-02-14 06:00:40 +01:00
|
|
|
/*
|
|
|
|
|
* Because O_DIRECT bypasses the kernel buffers, and because we never
|
|
|
|
|
* read those buffers except during crash recovery, it is a win to use
|
|
|
|
|
* it in all cases where we sync on each write(). We could allow O_DIRECT
|
|
|
|
|
* with fsync(), but because skipping the kernel buffer forces writes out
|
|
|
|
|
* quickly, it seems best just to use it for O_SYNC. It is hard to imagine
|
|
|
|
|
* how fsync() could be a win for O_DIRECT compared to O_SYNC and O_DIRECT.
|
|
|
|
|
* Also, O_DIRECT is never enough to force data to the drives, it merely
|
|
|
|
|
* tries to bypass the kernel cache, so we still need O_SYNC or fsync().
|
|
|
|
|
*/
|
|
|
|
|
#ifdef O_DIRECT
|
|
|
|
|
#define PG_O_DIRECT O_DIRECT
|
|
|
|
|
#else
|
|
|
|
|
#define PG_O_DIRECT 0
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* This chunk of hackery attempts to determine which file sync methods
|
|
|
|
|
* are available on the current platform, and to choose an appropriate
|
|
|
|
|
* default method. We assume that fsync() is always available, and that
|
|
|
|
|
* configure determined whether fdatasync() is.
|
|
|
|
|
*/
|
|
|
|
|
#if defined(O_SYNC)
|
|
|
|
|
#define BARE_OPEN_SYNC_FLAG O_SYNC
|
|
|
|
|
#elif defined(O_FSYNC)
|
|
|
|
|
#define BARE_OPEN_SYNC_FLAG O_FSYNC
|
|
|
|
|
#endif
|
|
|
|
|
#ifdef BARE_OPEN_SYNC_FLAG
|
|
|
|
|
#define OPEN_SYNC_FLAG (BARE_OPEN_SYNC_FLAG | PG_O_DIRECT)
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#if defined(O_DSYNC)
|
|
|
|
|
#if defined(OPEN_SYNC_FLAG)
|
|
|
|
|
/* O_DSYNC is distinct? */
|
|
|
|
|
#if O_DSYNC != BARE_OPEN_SYNC_FLAG
|
|
|
|
|
#define OPEN_DATASYNC_FLAG (O_DSYNC | PG_O_DIRECT)
|
|
|
|
|
#endif
|
|
|
|
|
#else /* !defined(OPEN_SYNC_FLAG) */
|
|
|
|
|
/* Win32 only has O_DSYNC */
|
|
|
|
|
#define OPEN_DATASYNC_FLAG (O_DSYNC | PG_O_DIRECT)
|
|
|
|
|
#endif
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#if defined(OPEN_DATASYNC_FLAG)
|
|
|
|
|
#define DEFAULT_SYNC_METHOD_STR "open_datasync"
|
|
|
|
|
#define DEFAULT_SYNC_METHOD SYNC_METHOD_OPEN
|
|
|
|
|
#define DEFAULT_SYNC_FLAGBIT OPEN_DATASYNC_FLAG
|
|
|
|
|
#elif defined(HAVE_FDATASYNC)
|
|
|
|
|
#define DEFAULT_SYNC_METHOD_STR "fdatasync"
|
|
|
|
|
#define DEFAULT_SYNC_METHOD SYNC_METHOD_FDATASYNC
|
|
|
|
|
#define DEFAULT_SYNC_FLAGBIT 0
|
|
|
|
|
#elif defined(HAVE_FSYNC_WRITETHROUGH_ONLY)
|
|
|
|
|
#define DEFAULT_SYNC_METHOD_STR "fsync_writethrough"
|
|
|
|
|
#define DEFAULT_SYNC_METHOD SYNC_METHOD_FSYNC_WRITETHROUGH
|
|
|
|
|
#define DEFAULT_SYNC_FLAGBIT 0
|
|
|
|
|
#else
|
|
|
|
|
#define DEFAULT_SYNC_METHOD_STR "fsync"
|
|
|
|
|
#define DEFAULT_SYNC_METHOD SYNC_METHOD_FSYNC
|
|
|
|
|
#define DEFAULT_SYNC_FLAGBIT 0
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Limitation of buffer-alignment for direct IO depends on OS and filesystem,
|
|
|
|
|
* but XLOG_BLCKSZ is assumed to be enough for it.
|
|
|
|
|
*/
|
|
|
|
|
#ifdef O_DIRECT
|
|
|
|
|
#define ALIGNOF_XLOG_BUFFER XLOG_BLCKSZ
|
|
|
|
|
#else
|
|
|
|
|
#define ALIGNOF_XLOG_BUFFER ALIGNOF_BUFFER
|
|
|
|
|
#endif
|
|
|
|
|
|
2001-11-05 18:46:40 +01:00
|
|
|
#endif /* XLOG_DEFS_H */
|
