#include <dirent.h>
#include <unistd.h>
-#include "access/xlog.h"
#include "access/xlogreader.h"
+#include "access/xlogrecord.h"
#include "access/transam.h"
#include "common/fe_memutils.h"
#include "getopt_long.h"
<para>
There are two commonly used internal <acronym>WAL</acronym> functions:
- <function>XLogInsert</function> and <function>XLogFlush</function>.
- <function>XLogInsert</function> is used to place a new record into
+ <function>XLogInsertRecord</function> and <function>XLogFlush</function>.
+ <function>XLogInsertRecord</function> is used to place a new record into
the <acronym>WAL</acronym> buffers in shared memory. If there is no
- space for the new record, <function>XLogInsert</function> will have
+ space for the new record, <function>XLogInsertRecord</function> will have
to write (move to kernel cache) a few filled <acronym>WAL</acronym>
- buffers. This is undesirable because <function>XLogInsert</function>
+ buffers. This is undesirable because <function>XLogInsertRecord</function>
is used on every database low level modification (for example, row
insertion) at a time when an exclusive lock is held on affected
data pages, so the operation needs to be as fast as possible. What
made, for the most part, at transaction commit time to ensure that
transaction records are flushed to permanent storage. On systems
with high log output, <function>XLogFlush</function> requests might
- not occur often enough to prevent <function>XLogInsert</function>
+ not occur often enough to prevent <function>XLogInsertRecord</function>
from having to do writes. On such systems
one should increase the number of <acronym>WAL</acronym> buffers by
modifying the <xref linkend="guc-wal-buffers"> parameter. When
Enabling the <xref linkend="guc-wal-debug"> configuration parameter
(provided that <productname>PostgreSQL</productname> has been
compiled with support for it) will result in each
- <function>XLogInsert</function> and <function>XLogFlush</function>
+ <function>XLogInsertRecord</function> and <function>XLogFlush</function>
<acronym>WAL</acronym> call being logged to the server log. This
option might be replaced by a more general mechanism in the future.
</para>
building the server). Each segment is divided into pages, normally
8 kB each (this size can be changed via the <option>--with-wal-blocksize</>
configure option). The log record headers are described in
- <filename>access/xlog.h</filename>; the record content is dependent
+ <filename>access/xlogrecord.h</filename>; the record content is dependent
on the type of event that is being logged. Segment files are given
ever-increasing numbers as names, starting at
<filename>000000010000000000000000</filename>. The numbers do not wrap,
#include "postgres.h"
#include "access/gin_private.h"
+#include "access/xloginsert.h"
#include "miscadmin.h"
#include "utils/rel.h"
#include "postgres.h"
#include "access/gin_private.h"
+#include "access/xloginsert.h"
#include "lib/ilist.h"
#include "miscadmin.h"
#include "utils/memutils.h"
#include "postgres.h"
#include "access/gin_private.h"
+#include "access/xloginsert.h"
#include "miscadmin.h"
#include "utils/rel.h"
#include "postgres.h"
#include "access/gin_private.h"
+#include "access/xloginsert.h"
#include "commands/vacuum.h"
#include "miscadmin.h"
#include "utils/memutils.h"
#include "postgres.h"
#include "access/gin_private.h"
+#include "access/xloginsert.h"
#include "catalog/index.h"
#include "miscadmin.h"
#include "storage/bufmgr.h"
#include "access/gin_private.h"
#include "access/reloptions.h"
+#include "access/xloginsert.h"
#include "catalog/pg_collation.h"
#include "catalog/pg_type.h"
#include "miscadmin.h"
#include "postgres.h"
#include "access/gin_private.h"
+#include "access/xloginsert.h"
#include "commands/vacuum.h"
#include "miscadmin.h"
#include "postmaster/autovacuum.h"
#include "access/genam.h"
#include "access/gist_private.h"
+#include "access/xloginsert.h"
#include "catalog/index.h"
#include "miscadmin.h"
#include "optimizer/cost.h"
#include "postgres.h"
#include "access/gist_private.h"
+#include "access/xloginsert.h"
#include "access/xlogutils.h"
#include "utils/memutils.h"
#include "access/valid.h"
#include "access/visibilitymap.h"
#include "access/xact.h"
+#include "access/xlog.h"
+#include "access/xloginsert.h"
#include "access/xlogutils.h"
#include "catalog/catalog.h"
#include "catalog/namespace.h"
#include "access/heapam_xlog.h"
#include "access/transam.h"
#include "access/htup_details.h"
+#include "access/xlog.h"
#include "catalog/catalog.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "access/transam.h"
#include "access/tuptoaster.h"
#include "access/xact.h"
+#include "access/xloginsert.h"
#include "catalog/catalog.h"
#include "access/heapam_xlog.h"
#include "access/visibilitymap.h"
+#include "access/xlog.h"
#include "miscadmin.h"
#include "storage/bufmgr.h"
#include "storage/lmgr.h"
#include "access/heapam.h"
#include "access/nbtree.h"
#include "access/transam.h"
+#include "access/xloginsert.h"
#include "miscadmin.h"
#include "storage/lmgr.h"
#include "storage/predicate.h"
#include "access/nbtree.h"
#include "access/transam.h"
+#include "access/xlog.h"
+#include "access/xloginsert.h"
#include "miscadmin.h"
#include "storage/indexfsm.h"
#include "storage/lmgr.h"
#include "access/nbtree.h"
#include "access/relscan.h"
+#include "access/xlog.h"
#include "catalog/index.h"
#include "commands/vacuum.h"
#include "storage/indexfsm.h"
#include "postgres.h"
#include "access/nbtree.h"
+#include "access/xlog.h"
+#include "access/xloginsert.h"
#include "miscadmin.h"
#include "storage/smgr.h"
#include "tcop/tcopprot.h"
#include "access/heapam_xlog.h"
#include "access/nbtree.h"
#include "access/transam.h"
+#include "access/xlog.h"
+#include "access/xlogutils.h"
#include "storage/procarray.h"
#include "miscadmin.h"
#include "postgres.h"
#include "access/genam.h"
+#include "access/xloginsert.h"
#include "access/spgist_private.h"
#include "miscadmin.h"
#include "storage/bufmgr.h"
#include "access/genam.h"
#include "access/spgist_private.h"
+#include "access/xlog.h"
+#include "access/xloginsert.h"
#include "catalog/index.h"
#include "miscadmin.h"
#include "storage/bufmgr.h"
#include "access/genam.h"
#include "access/spgist_private.h"
#include "access/transam.h"
+#include "access/xloginsert.h"
#include "catalog/storage_xlog.h"
#include "commands/vacuum.h"
#include "miscadmin.h"
#include "access/spgist_private.h"
#include "access/transam.h"
+#include "access/xlog.h"
#include "access/xlogutils.h"
#include "storage/standby.h"
#include "utils/memutils.h"
OBJS = clog.o transam.o varsup.o xact.o rmgr.o slru.o subtrans.o multixact.o \
timeline.o twophase.o twophase_rmgr.o xlog.o xlogarchive.o xlogfuncs.o \
- xlogreader.o xlogutils.o
+ xloginsert.o xlogreader.o xlogutils.o
include $(top_srcdir)/src/backend/common.mk
#include "access/clog.h"
#include "access/slru.h"
#include "access/transam.h"
+#include "access/xlog.h"
+#include "access/xloginsert.h"
+#include "access/xlogutils.h"
#include "miscadmin.h"
#include "pg_trace.h"
#include "access/twophase.h"
#include "access/twophase_rmgr.h"
#include "access/xact.h"
+#include "access/xlog.h"
+#include "access/xloginsert.h"
#include "catalog/pg_type.h"
#include "commands/dbcommands.h"
#include "funcapi.h"
#include "access/twophase_rmgr.h"
#include "access/xact.h"
#include "access/xlog.h"
+#include "access/xloginsert.h"
#include "access/xlogutils.h"
#include "catalog/pg_type.h"
#include "catalog/storage.h"
#include "access/subtrans.h"
#include "access/transam.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "commands/dbcommands.h"
#include "miscadmin.h"
#include "postmaster/autovacuum.h"
#include "access/transam.h"
#include "access/twophase.h"
#include "access/xact.h"
+#include "access/xlog.h"
+#include "access/xloginsert.h"
#include "access/xlogutils.h"
#include "catalog/catalog.h"
#include "catalog/namespace.h"
#include "access/twophase.h"
#include "access/xact.h"
#include "access/xlog_internal.h"
+#include "access/xloginsert.h"
#include "access/xlogreader.h"
#include "access/xlogutils.h"
#include "catalog/catversion.h"
* (which is almost but not quite the same as a pointer to the most recent
* CHECKPOINT record). We update this from the shared-memory copy,
* XLogCtl->Insert.RedoRecPtr, whenever we can safely do so (ie, when we
- * hold an insertion lock). See XLogInsert for details. We are also allowed
- * to update from XLogCtl->RedoRecPtr if we hold the info_lck;
+ * hold an insertion lock). See XLogInsertRecord for details. We are also
+ * allowed to update from XLogCtl->RedoRecPtr if we hold the info_lck;
* see GetRedoRecPtr. A freshly spawned backend obtains the value during
* InitXLOGAccess.
*/
static XLogRecPtr RedoRecPtr;
+/*
+ * doPageWrites is this backend's local copy of (forcePageWrites ||
+ * fullPageWrites). It is used together with RedoRecPtr to decide whether
+ * a full-page image of a page need to be taken.
+ */
+static bool doPageWrites;
+
/*
* RedoStartLSN points to the checkpoint's REDO location which is specified
* in a backup label file, backup history file or control file. In standby
} WALInsertLockPadded;
/*
- * Shared state data for XLogInsert.
+ * Shared state data for WAL insertion.
*/
typedef struct XLogCtlInsert
{
static void KeepLogSeg(XLogRecPtr recptr, XLogSegNo *logSegNo);
static XLogRecPtr XLogGetReplicationSlotMinimumLSN(void);
-static bool XLogCheckBuffer(XLogRecData *rdata, bool holdsExclusiveLock,
- XLogRecPtr *lsn, BkpBlock *bkpb);
-static Buffer RestoreBackupBlockContents(XLogRecPtr lsn, BkpBlock bkpb,
- char *blk, bool get_cleanup_lock, bool keep_buffer);
static void AdvanceXLInsertBuffer(XLogRecPtr upto, bool opportunistic);
static bool XLogCheckpointNeeded(XLogSegNo new_segno);
static void XLogWrite(XLogwrtRqst WriteRqst, bool flexible);
static void WALInsertLockUpdateInsertingAt(XLogRecPtr insertingAt);
/*
- * Insert an XLOG record having the specified RMID and info bytes,
- * with the body of the record being the data chunk(s) described by
- * the rdata chain (see xlog.h for notes about rdata).
+ * Insert an XLOG record represented by an already-constructed chain of data
+ * chunks. This is a low-level routine; to construct the WAL record header
+ * and data, use the higher-level routines in xloginsert.c.
+ *
+ * If 'fpw_lsn' is valid, it is the oldest LSN among the pages that this
+ * WAL record applies to, that were not included in the record as full page
+ * images. If fpw_lsn >= RedoRecPtr, the function does not perform the
+ * insertion and returns InvalidXLogRecPtr. The caller can then recalculate
+ * which pages need a full-page image, and retry. If fpw_lsn is invalid, the
+ * record is always inserted.
+ *
+ * The first XLogRecData in the chain must be for the record header, and its
+ * data must be MAXALIGNed. XLogInsertRecord fills in the xl_prev and
+ * xl_crc fields in the header, the rest of the header must already be filled
+ * by the caller.
*
* Returns XLOG pointer to end of record (beginning of next record).
* This can be used as LSN for data pages affected by the logged action.
* (LSN is the XLOG point up to which the XLOG must be flushed to disk
* before the data page can be written out. This implements the basic
* WAL rule "write the log before the data".)
- *
- * NB: this routine feels free to scribble on the XLogRecData structs,
- * though not on the data they reference. This is OK since the XLogRecData
- * structs are always just temporaries in the calling code.
*/
XLogRecPtr
-XLogInsert(RmgrId rmid, uint8 info, XLogRecData *rdata)
+XLogInsertRecord(XLogRecData *rdata, XLogRecPtr fpw_lsn)
{
XLogCtlInsert *Insert = &XLogCtl->Insert;
XLogRecData *rdt;
- XLogRecData *rdt_lastnormal;
- Buffer dtbuf[XLR_MAX_BKP_BLOCKS];
- bool dtbuf_bkp[XLR_MAX_BKP_BLOCKS];
- BkpBlock dtbuf_xlg[XLR_MAX_BKP_BLOCKS];
- XLogRecPtr dtbuf_lsn[XLR_MAX_BKP_BLOCKS];
- XLogRecData dtbuf_rdt1[XLR_MAX_BKP_BLOCKS];
- XLogRecData dtbuf_rdt2[XLR_MAX_BKP_BLOCKS];
- XLogRecData dtbuf_rdt3[XLR_MAX_BKP_BLOCKS];
- XLogRecData hdr_rdt;
pg_crc32 rdata_crc;
- uint32 len,
- write_len;
- unsigned i;
- bool doPageWrites;
- bool isLogSwitch = (rmid == RM_XLOG_ID && info == XLOG_SWITCH);
bool inserted;
- uint8 info_orig = info;
- static XLogRecord *rechdr;
+ XLogRecord *rechdr = (XLogRecord *) rdata->data;
+ bool isLogSwitch = (rechdr->xl_rmid == RM_XLOG_ID &&
+ rechdr->xl_info == XLOG_SWITCH);
XLogRecPtr StartPos;
XLogRecPtr EndPos;
- if (rechdr == NULL)
- {
- static char rechdrbuf[SizeOfXLogRecord + MAXIMUM_ALIGNOF];
-
- rechdr = (XLogRecord *) MAXALIGN(&rechdrbuf);
- MemSet(rechdr, 0, SizeOfXLogRecord);
- }
-
/* cross-check on whether we should be here or not */
if (!XLogInsertAllowed())
elog(ERROR, "cannot make new WAL entries during recovery");
- /* info's high bits are reserved for use by me */
- if (info & XLR_INFO_MASK)
- elog(PANIC, "invalid xlog info mask %02X", info);
-
- TRACE_POSTGRESQL_XLOG_INSERT(rmid, info);
-
- /*
- * In bootstrap mode, we don't actually log anything but XLOG resources;
- * return a phony record pointer.
- */
- if (IsBootstrapProcessingMode() && rmid != RM_XLOG_ID)
- {
- EndPos = SizeOfXLogLongPHD; /* start of 1st chkpt record */
- return EndPos;
- }
-
- /*
- * Here we scan the rdata chain, to determine which buffers must be backed
- * up.
- *
- * We may have to loop back to here if a race condition is detected below.
- * We could prevent the race by doing all this work while holding an
- * insertion lock, but it seems better to avoid doing CRC calculations
- * while holding one.
- *
- * We add entries for backup blocks to the chain, so that they don't need
- * any special treatment in the critical section where the chunks are
- * copied into the WAL buffers. Those entries have to be unlinked from the
- * chain if we have to loop back here.
- */
-begin:;
- for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
- {
- dtbuf[i] = InvalidBuffer;
- dtbuf_bkp[i] = false;
- }
-
- /*
- * Decide if we need to do full-page writes in this XLOG record: true if
- * full_page_writes is on or we have a PITR request for it. Since we
- * don't yet have an insertion lock, fullPageWrites and forcePageWrites
- * could change under us, but we'll recheck them once we have a lock.
- */
- doPageWrites = Insert->fullPageWrites || Insert->forcePageWrites;
-
- len = 0;
- for (rdt = rdata;;)
- {
- if (rdt->buffer == InvalidBuffer)
- {
- /* Simple data, just include it */
- len += rdt->len;
- }
- else
- {
- /* Find info for buffer */
- for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
- {
- if (rdt->buffer == dtbuf[i])
- {
- /* Buffer already referenced by earlier chain item */
- if (dtbuf_bkp[i])
- {
- rdt->data = NULL;
- rdt->len = 0;
- }
- else if (rdt->data)
- len += rdt->len;
- break;
- }
- if (dtbuf[i] == InvalidBuffer)
- {
- /* OK, put it in this slot */
- dtbuf[i] = rdt->buffer;
- if (doPageWrites && XLogCheckBuffer(rdt, true,
- &(dtbuf_lsn[i]), &(dtbuf_xlg[i])))
- {
- dtbuf_bkp[i] = true;
- rdt->data = NULL;
- rdt->len = 0;
- }
- else if (rdt->data)
- len += rdt->len;
- break;
- }
- }
- if (i >= XLR_MAX_BKP_BLOCKS)
- elog(PANIC, "can backup at most %d blocks per xlog record",
- XLR_MAX_BKP_BLOCKS);
- }
- /* Break out of loop when rdt points to last chain item */
- if (rdt->next == NULL)
- break;
- rdt = rdt->next;
- }
-
- /*
- * NOTE: We disallow len == 0 because it provides a useful bit of extra
- * error checking in ReadRecord. This means that all callers of
- * XLogInsert must supply at least some not-in-a-buffer data. However, we
- * make an exception for XLOG SWITCH records because we don't want them to
- * ever cross a segment boundary.
- */
- if (len == 0 && !isLogSwitch)
- elog(PANIC, "invalid xlog record length %u", len);
-
- /*
- * Make additional rdata chain entries for the backup blocks, so that we
- * don't need to special-case them in the write loop. This modifies the
- * original rdata chain, but we keep a pointer to the last regular entry,
- * rdt_lastnormal, so that we can undo this if we have to loop back to the
- * beginning.
- *
- * At the exit of this loop, write_len includes the backup block data.
- *
- * Also set the appropriate info bits to show which buffers were backed
- * up. The XLR_BKP_BLOCK(N) bit corresponds to the N'th distinct buffer
- * value (ignoring InvalidBuffer) appearing in the rdata chain.
- */
- rdt_lastnormal = rdt;
- write_len = len;
- for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
- {
- BkpBlock *bkpb;
- char *page;
-
- if (!dtbuf_bkp[i])
- continue;
-
- info |= XLR_BKP_BLOCK(i);
-
- bkpb = &(dtbuf_xlg[i]);
- page = (char *) BufferGetBlock(dtbuf[i]);
-
- rdt->next = &(dtbuf_rdt1[i]);
- rdt = rdt->next;
-
- rdt->data = (char *) bkpb;
- rdt->len = sizeof(BkpBlock);
- write_len += sizeof(BkpBlock);
-
- rdt->next = &(dtbuf_rdt2[i]);
- rdt = rdt->next;
-
- if (bkpb->hole_length == 0)
- {
- rdt->data = page;
- rdt->len = BLCKSZ;
- write_len += BLCKSZ;
- rdt->next = NULL;
- }
- else
- {
- /* must skip the hole */
- rdt->data = page;
- rdt->len = bkpb->hole_offset;
- write_len += bkpb->hole_offset;
-
- rdt->next = &(dtbuf_rdt3[i]);
- rdt = rdt->next;
-
- rdt->data = page + (bkpb->hole_offset + bkpb->hole_length);
- rdt->len = BLCKSZ - (bkpb->hole_offset + bkpb->hole_length);
- write_len += rdt->len;
- rdt->next = NULL;
- }
- }
-
/*
* Calculate CRC of the data, including all the backup blocks
*
* header.
*/
INIT_CRC32C(rdata_crc);
- for (rdt = rdata; rdt != NULL; rdt = rdt->next)
+ for (rdt = rdata->next; rdt != NULL; rdt = rdt->next)
COMP_CRC32C(rdata_crc, rdt->data, rdt->len);
/*
- * Construct record header (prev-link is filled in later, after reserving
- * the space for the record), and make that the first chunk in the chain.
- *
- * The CRC calculated for the header here doesn't include prev-link,
- * because we don't know it yet. It will be added later.
- */
- rechdr->xl_xid = GetCurrentTransactionIdIfAny();
- rechdr->xl_tot_len = SizeOfXLogRecord + write_len;
- rechdr->xl_len = len; /* doesn't include backup blocks */
- rechdr->xl_info = info;
- rechdr->xl_rmid = rmid;
- rechdr->xl_prev = InvalidXLogRecPtr;
+ * Calculate CRC of the header, except for prev-link, because we don't
+ * know it yet. It will be added later.
+ */
COMP_CRC32C(rdata_crc, ((char *) rechdr), offsetof(XLogRecord, xl_prev));
- hdr_rdt.next = rdata;
- hdr_rdt.data = (char *) rechdr;
- hdr_rdt.len = SizeOfXLogRecord;
- write_len += SizeOfXLogRecord;
-
/*----------
*
* We have now done all the preparatory work we can without holding a
WALInsertLockAcquire();
/*
- * Check to see if my RedoRecPtr is out of date. If so, may have to go
- * back and recompute everything. This can only happen just after a
- * checkpoint, so it's better to be slow in this case and fast otherwise.
+ * Check to see if my copy of RedoRecPtr or doPageWrites is out of date.
+ * If so, may have to go back and have the caller recompute everything.
+ * This can only happen just after a checkpoint, so it's better to be
+ * slow in this case and fast otherwise.
*
* If we aren't doing full-page writes then RedoRecPtr doesn't actually
* affect the contents of the XLOG record, so we'll update our local copy
- * but not force a recomputation.
+ * but not force a recomputation. (If doPageWrites was just turned off,
+ * we could recompute the record without full pages, but we choose not
+ * to bother.)
*/
if (RedoRecPtr != Insert->RedoRecPtr)
{
Assert(RedoRecPtr < Insert->RedoRecPtr);
RedoRecPtr = Insert->RedoRecPtr;
-
- if (doPageWrites)
- {
- for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
- {
- if (dtbuf[i] == InvalidBuffer)
- continue;
- if (dtbuf_bkp[i] == false &&
- dtbuf_lsn[i] <= RedoRecPtr)
- {
- /*
- * Oops, this buffer now needs to be backed up, but we
- * didn't think so above. Start over.
- */
- WALInsertLockRelease();
- END_CRIT_SECTION();
- rdt_lastnormal->next = NULL;
- info = info_orig;
- goto begin;
- }
- }
- }
}
+ doPageWrites = (Insert->fullPageWrites || Insert->forcePageWrites);
- /*
- * Also check to see if fullPageWrites or forcePageWrites was just turned
- * on; if we weren't already doing full-page writes then go back and
- * recompute. (If it was just turned off, we could recompute the record
- * without full pages, but we choose not to bother.)
- */
- if ((Insert->fullPageWrites || Insert->forcePageWrites) && !doPageWrites)
+ if (fpw_lsn != InvalidXLogRecPtr && fpw_lsn <= RedoRecPtr && doPageWrites)
{
- /* Oops, must redo it with full-page data. */
+ /*
+ * Oops, some buffer now needs to be backed up that the caller
+ * didn't back up. Start over.
+ */
WALInsertLockRelease();
END_CRIT_SECTION();
- rdt_lastnormal->next = NULL;
- info = info_orig;
- goto begin;
+ return InvalidXLogRecPtr;
}
/*
inserted = ReserveXLogSwitch(&StartPos, &EndPos, &rechdr->xl_prev);
else
{
- ReserveXLogInsertLocation(write_len, &StartPos, &EndPos,
+ ReserveXLogInsertLocation(rechdr->xl_tot_len, &StartPos, &EndPos,
&rechdr->xl_prev);
inserted = true;
}
* All the record data, including the header, is now ready to be
* inserted. Copy the record in the space reserved.
*/
- CopyXLogRecordToWAL(write_len, isLogSwitch, &hdr_rdt, StartPos, EndPos);
+ CopyXLogRecordToWAL(rechdr->xl_tot_len, isLogSwitch, rdata,
+ StartPos, EndPos);
}
else
{
}
/*
- * Subroutine of XLogInsert. Copies a WAL record to an already-reserved
+ * Subroutine of XLogInsertRecord. Copies a WAL record to an already-reserved
* area in the WAL.
*/
static void
return result;
}
-/*
- * Determine whether the buffer referenced has to be backed up.
- *
- * Since we don't yet have the insert lock, fullPageWrites and forcePageWrites
- * could change later, so the result should be used for optimization purposes
- * only.
- */
-bool
-XLogCheckBufferNeedsBackup(Buffer buffer)
-{
- bool doPageWrites;
- Page page;
-
- page = BufferGetPage(buffer);
-
- doPageWrites = XLogCtl->Insert.fullPageWrites || XLogCtl->Insert.forcePageWrites;
-
- if (doPageWrites && PageGetLSN(page) <= RedoRecPtr)
- return true; /* buffer requires backup */
-
- return false; /* buffer does not need to be backed up */
-}
-
-/*
- * Determine whether the buffer referenced by an XLogRecData item has to
- * be backed up, and if so fill a BkpBlock struct for it. In any case
- * save the buffer's LSN at *lsn.
- */
-static bool
-XLogCheckBuffer(XLogRecData *rdata, bool holdsExclusiveLock,
- XLogRecPtr *lsn, BkpBlock *bkpb)
-{
- Page page;
-
- page = BufferGetPage(rdata->buffer);
-
- /*
- * We assume page LSN is first data on *every* page that can be passed to
- * XLogInsert, whether it has the standard page layout or not. We don't
- * need to take the buffer header lock for PageGetLSN if we hold an
- * exclusive lock on the page and/or the relation.
- */
- if (holdsExclusiveLock)
- *lsn = PageGetLSN(page);
- else
- *lsn = BufferGetLSNAtomic(rdata->buffer);
-
- if (*lsn <= RedoRecPtr)
- {
- /*
- * The page needs to be backed up, so set up *bkpb
- */
- BufferGetTag(rdata->buffer, &bkpb->node, &bkpb->fork, &bkpb->block);
-
- if (rdata->buffer_std)
- {
- /* Assume we can omit data between pd_lower and pd_upper */
- uint16 lower = ((PageHeader) page)->pd_lower;
- uint16 upper = ((PageHeader) page)->pd_upper;
-
- if (lower >= SizeOfPageHeaderData &&
- upper > lower &&
- upper <= BLCKSZ)
- {
- bkpb->hole_offset = lower;
- bkpb->hole_length = upper - lower;
- }
- else
- {
- /* No "hole" to compress out */
- bkpb->hole_offset = 0;
- bkpb->hole_length = 0;
- }
- }
- else
- {
- /* Not a standard page header, don't try to eliminate "hole" */
- bkpb->hole_offset = 0;
- bkpb->hole_length = 0;
- }
-
- return true; /* buffer requires backup */
- }
-
- return false; /* buffer does not need to be backed up */
-}
-
/*
* Initialize XLOG buffers, writing out old buffers if they still contain
* unwritten data, upto the page containing 'upto'. Or if 'opportunistic' is
FreeDir(xldir);
}
-/*
- * Restore a full-page image from a backup block attached to an XLOG record.
- *
- * lsn: LSN of the XLOG record being replayed
- * record: the complete XLOG record
- * block_index: which backup block to restore (0 .. XLR_MAX_BKP_BLOCKS - 1)
- * get_cleanup_lock: TRUE to get a cleanup rather than plain exclusive lock
- * keep_buffer: TRUE to return the buffer still locked and pinned
- *
- * Returns the buffer number containing the page. Note this is not terribly
- * useful unless keep_buffer is specified as TRUE.
- *
- * Note: when a backup block is available in XLOG, we restore it
- * unconditionally, even if the page in the database appears newer.
- * This is to protect ourselves against database pages that were partially
- * or incorrectly written during a crash. We assume that the XLOG data
- * must be good because it has passed a CRC check, while the database
- * page might not be. This will force us to replay all subsequent
- * modifications of the page that appear in XLOG, rather than possibly
- * ignoring them as already applied, but that's not a huge drawback.
- *
- * If 'get_cleanup_lock' is true, a cleanup lock is obtained on the buffer,
- * else a normal exclusive lock is used. During crash recovery, that's just
- * pro forma because there can't be any regular backends in the system, but
- * in hot standby mode the distinction is important.
- *
- * If 'keep_buffer' is true, return without releasing the buffer lock and pin;
- * then caller is responsible for doing UnlockReleaseBuffer() later. This
- * is needed in some cases when replaying XLOG records that touch multiple
- * pages, to prevent inconsistent states from being visible to other backends.
- * (Again, that's only important in hot standby mode.)
- */
-Buffer
-RestoreBackupBlock(XLogRecPtr lsn, XLogRecord *record, int block_index,
- bool get_cleanup_lock, bool keep_buffer)
-{
- BkpBlock bkpb;
- char *blk;
- int i;
-
- /* Locate requested BkpBlock in the record */
- blk = (char *) XLogRecGetData(record) + record->xl_len;
- for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
- {
- if (!(record->xl_info & XLR_BKP_BLOCK(i)))
- continue;
-
- memcpy(&bkpb, blk, sizeof(BkpBlock));
- blk += sizeof(BkpBlock);
-
- if (i == block_index)
- {
- /* Found it, apply the update */
- return RestoreBackupBlockContents(lsn, bkpb, blk, get_cleanup_lock,
- keep_buffer);
- }
-
- blk += BLCKSZ - bkpb.hole_length;
- }
-
- /* Caller specified a bogus block_index */
- elog(ERROR, "failed to restore block_index %d", block_index);
- return InvalidBuffer; /* keep compiler quiet */
-}
-
-/*
- * Workhorse for RestoreBackupBlock usable without an xlog record
- *
- * Restores a full-page image from BkpBlock and a data pointer.
- */
-static Buffer
-RestoreBackupBlockContents(XLogRecPtr lsn, BkpBlock bkpb, char *blk,
- bool get_cleanup_lock, bool keep_buffer)
-{
- Buffer buffer;
- Page page;
-
- buffer = XLogReadBufferExtended(bkpb.node, bkpb.fork, bkpb.block,
- RBM_ZERO);
- Assert(BufferIsValid(buffer));
- if (get_cleanup_lock)
- LockBufferForCleanup(buffer);
- else
- LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
-
- page = (Page) BufferGetPage(buffer);
-
- if (bkpb.hole_length == 0)
- {
- memcpy((char *) page, blk, BLCKSZ);
- }
- else
- {
- memcpy((char *) page, blk, bkpb.hole_offset);
- /* must zero-fill the hole */
- MemSet((char *) page + bkpb.hole_offset, 0, bkpb.hole_length);
- memcpy((char *) page + (bkpb.hole_offset + bkpb.hole_length),
- blk + bkpb.hole_offset,
- BLCKSZ - (bkpb.hole_offset + bkpb.hole_length));
- }
-
- /*
- * The checksum value on this page is currently invalid. We don't need to
- * reset it here since it will be set before being written.
- */
-
- /*
- * The page may be uninitialized. If so, we can't set the LSN because that
- * would corrupt the page.
- */
- if (!PageIsNew(page))
- {
- PageSetLSN(page, lsn);
- }
- MarkBufferDirty(buffer);
-
- if (!keep_buffer)
- UnlockReleaseBuffer(buffer);
-
- return buffer;
-}
-
/*
* Attempt to read an XLOG record.
*
lastFullPageWrites = checkPoint.fullPageWrites;
RedoRecPtr = XLogCtl->RedoRecPtr = XLogCtl->Insert.RedoRecPtr = checkPoint.redo;
+ doPageWrites = lastFullPageWrites;
if (RecPtr < checkPoint.redo)
ereport(PANIC,
void
InitXLOGAccess(void)
{
+ XLogCtlInsert *Insert = &XLogCtl->Insert;
+
/* ThisTimeLineID doesn't change so we need no lock to copy it */
ThisTimeLineID = XLogCtl->ThisTimeLineID;
Assert(ThisTimeLineID != 0 || IsBootstrapProcessingMode());
/* Use GetRedoRecPtr to copy the RedoRecPtr safely */
(void) GetRedoRecPtr();
+ /* Also update our copy of doPageWrites. */
+ doPageWrites = (Insert->fullPageWrites || Insert->forcePageWrites);
}
/*
return RedoRecPtr;
}
+/*
+ * Return information needed to decide whether a modified block needs a
+ * full-page image to be included in the WAL record.
+ *
+ * The returned values are cached copies from backend-private memory, and
+ * possibly out-of-date. XLogInsertRecord will re-check them against
+ * up-to-date values, while holding the WAL insert lock.
+ */
+void
+GetFullPageWriteInfo(XLogRecPtr *RedoRecPtr_p, bool *doPageWrites_p)
+{
+ *RedoRecPtr_p = RedoRecPtr;
+ *doPageWrites_p = doPageWrites;
+}
+
/*
* GetInsertRecPtr -- Returns the current insert position.
*
return RecPtr;
}
-/*
- * Write a backup block if needed when we are setting a hint. Note that
- * this may be called for a variety of page types, not just heaps.
- *
- * Callable while holding just share lock on the buffer content.
- *
- * We can't use the plain backup block mechanism since that relies on the
- * Buffer being exclusively locked. Since some modifications (setting LSN, hint
- * bits) are allowed in a sharelocked buffer that can lead to wal checksum
- * failures. So instead we copy the page and insert the copied data as normal
- * record data.
- *
- * We only need to do something if page has not yet been full page written in
- * this checkpoint round. The LSN of the inserted wal record is returned if we
- * had to write, InvalidXLogRecPtr otherwise.
- *
- * It is possible that multiple concurrent backends could attempt to write WAL
- * records. In that case, multiple copies of the same block would be recorded
- * in separate WAL records by different backends, though that is still OK from
- * a correctness perspective.
- */
-XLogRecPtr
-XLogSaveBufferForHint(Buffer buffer, bool buffer_std)
-{
- XLogRecPtr recptr = InvalidXLogRecPtr;
- XLogRecPtr lsn;
- XLogRecData rdata[2];
- BkpBlock bkpb;
-
- /*
- * Ensure no checkpoint can change our view of RedoRecPtr.
- */
- Assert(MyPgXact->delayChkpt);
-
- /*
- * Update RedoRecPtr so XLogCheckBuffer can make the right decision
- */
- GetRedoRecPtr();
-
- /*
- * Setup phony rdata element for use within XLogCheckBuffer only. We reuse
- * and reset rdata for any actual WAL record insert.
- */
- rdata[0].buffer = buffer;
- rdata[0].buffer_std = buffer_std;
-
- /*
- * Check buffer while not holding an exclusive lock.
- */
- if (XLogCheckBuffer(rdata, false, &lsn, &bkpb))
- {
- char copied_buffer[BLCKSZ];
- char *origdata = (char *) BufferGetBlock(buffer);
-
- /*
- * Copy buffer so we don't have to worry about concurrent hint bit or
- * lsn updates. We assume pd_lower/upper cannot be changed without an
- * exclusive lock, so the contents bkp are not racy.
- *
- * With buffer_std set to false, XLogCheckBuffer() sets hole_length
- * and hole_offset to 0; so the following code is safe for either
- * case.
- */
- memcpy(copied_buffer, origdata, bkpb.hole_offset);
- memcpy(copied_buffer + bkpb.hole_offset,
- origdata + bkpb.hole_offset + bkpb.hole_length,
- BLCKSZ - bkpb.hole_offset - bkpb.hole_length);
-
- /*
- * Header for backup block.
- */
- rdata[0].data = (char *) &bkpb;
- rdata[0].len = sizeof(BkpBlock);
- rdata[0].buffer = InvalidBuffer;
- rdata[0].next = &(rdata[1]);
-
- /*
- * Save copy of the buffer.
- */
- rdata[1].data = copied_buffer;
- rdata[1].len = BLCKSZ - bkpb.hole_length;
- rdata[1].buffer = InvalidBuffer;
- rdata[1].next = NULL;
-
- recptr = XLogInsert(RM_XLOG_ID, XLOG_FPI, rdata);
- }
-
- return recptr;
-}
-
-/*
- * Write a WAL record containing a full image of a page. Caller is responsible
- * for writing the page to disk after calling this routine.
- *
- * Note: If you're using this function, you should be building pages in private
- * memory and writing them directly to smgr. If you're using buffers, call
- * log_newpage_buffer instead.
- *
- * If the page follows the standard page layout, with a PageHeader and unused
- * space between pd_lower and pd_upper, set 'page_std' to TRUE. That allows
- * the unused space to be left out from the WAL record, making it smaller.
- */
-XLogRecPtr
-log_newpage(RelFileNode *rnode, ForkNumber forkNum, BlockNumber blkno,
- Page page, bool page_std)
-{
- BkpBlock bkpb;
- XLogRecPtr recptr;
- XLogRecData rdata[3];
-
- /* NO ELOG(ERROR) from here till newpage op is logged */
- START_CRIT_SECTION();
-
- bkpb.node = *rnode;
- bkpb.fork = forkNum;
- bkpb.block = blkno;
-
- if (page_std)
- {
- /* Assume we can omit data between pd_lower and pd_upper */
- uint16 lower = ((PageHeader) page)->pd_lower;
- uint16 upper = ((PageHeader) page)->pd_upper;
-
- if (lower >= SizeOfPageHeaderData &&
- upper > lower &&
- upper <= BLCKSZ)
- {
- bkpb.hole_offset = lower;
- bkpb.hole_length = upper - lower;
- }
- else
- {
- /* No "hole" to compress out */
- bkpb.hole_offset = 0;
- bkpb.hole_length = 0;
- }
- }
- else
- {
- /* Not a standard page header, don't try to eliminate "hole" */
- bkpb.hole_offset = 0;
- bkpb.hole_length = 0;
- }
-
- rdata[0].data = (char *) &bkpb;
- rdata[0].len = sizeof(BkpBlock);
- rdata[0].buffer = InvalidBuffer;
- rdata[0].next = &(rdata[1]);
-
- if (bkpb.hole_length == 0)
- {
- rdata[1].data = (char *) page;
- rdata[1].len = BLCKSZ;
- rdata[1].buffer = InvalidBuffer;
- rdata[1].next = NULL;
- }
- else
- {
- /* must skip the hole */
- rdata[1].data = (char *) page;
- rdata[1].len = bkpb.hole_offset;
- rdata[1].buffer = InvalidBuffer;
- rdata[1].next = &rdata[2];
-
- rdata[2].data = (char *) page + (bkpb.hole_offset + bkpb.hole_length);
- rdata[2].len = BLCKSZ - (bkpb.hole_offset + bkpb.hole_length);
- rdata[2].buffer = InvalidBuffer;
- rdata[2].next = NULL;
- }
-
- recptr = XLogInsert(RM_XLOG_ID, XLOG_FPI, rdata);
-
- /*
- * The page may be uninitialized. If so, we can't set the LSN because that
- * would corrupt the page.
- */
- if (!PageIsNew(page))
- {
- PageSetLSN(page, recptr);
- }
-
- END_CRIT_SECTION();
-
- return recptr;
-}
-
-/*
- * Write a WAL record containing a full image of a page.
- *
- * Caller should initialize the buffer and mark it dirty before calling this
- * function. This function will set the page LSN.
- *
- * If the page follows the standard page layout, with a PageHeader and unused
- * space between pd_lower and pd_upper, set 'page_std' to TRUE. That allows
- * the unused space to be left out from the WAL record, making it smaller.
- */
-XLogRecPtr
-log_newpage_buffer(Buffer buffer, bool page_std)
-{
- Page page = BufferGetPage(buffer);
- RelFileNode rnode;
- ForkNumber forkNum;
- BlockNumber blkno;
-
- /* Shared buffers should be modified in a critical section. */
- Assert(CritSectionCount > 0);
-
- BufferGetTag(buffer, &rnode, &forkNum, &blkno);
-
- return log_newpage(&rnode, forkNum, blkno, page, page_std);
-}
-
/*
* Check if any of the GUC parameters that are critical for hot standby
* have changed, and update the value in pg_control file if necessary.
* the standby.
*
* We must hold all the insertion locks to change the value of
- * forcePageWrites, to ensure adequate interlocking against XLogInsert().
+ * forcePageWrites, to ensure adequate interlocking against
+ * XLogInsertRecord().
*/
WALInsertLockAcquireExclusive();
if (exclusive)
--- /dev/null
+/*-------------------------------------------------------------------------
+ *
+ * xloginsert.c
+ * Functions for constructing WAL records
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/backend/access/transam/xloginsert.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include "access/xact.h"
+#include "access/xlog.h"
+#include "access/xlog_internal.h"
+#include "access/xloginsert.h"
+#include "catalog/pg_control.h"
+#include "miscadmin.h"
+#include "storage/bufmgr.h"
+#include "storage/proc.h"
+#include "utils/memutils.h"
+#include "pg_trace.h"
+
+static XLogRecData *XLogRecordAssemble(RmgrId rmid, uint8 info,
+ XLogRecData *rdata,
+ XLogRecPtr RedoRecPtr, bool doPageWrites,
+ XLogRecPtr *fpw_lsn, XLogRecData **rdt_lastnormal);
+static void XLogFillBkpBlock(Buffer buffer, bool buffer_std, BkpBlock *bkpb);
+
+/*
+ * Insert an XLOG record having the specified RMID and info bytes,
+ * with the body of the record being the data chunk(s) described by
+ * the rdata chain (see xloginsert.h for notes about rdata).
+ *
+ * Returns XLOG pointer to end of record (beginning of next record).
+ * This can be used as LSN for data pages affected by the logged action.
+ * (LSN is the XLOG point up to which the XLOG must be flushed to disk
+ * before the data page can be written out. This implements the basic
+ * WAL rule "write the log before the data".)
+ *
+ * NB: this routine feels free to scribble on the XLogRecData structs,
+ * though not on the data they reference. This is OK since the XLogRecData
+ * structs are always just temporaries in the calling code.
+ */
+XLogRecPtr
+XLogInsert(RmgrId rmid, uint8 info, XLogRecData *rdata)
+{
+ XLogRecPtr RedoRecPtr;
+ bool doPageWrites;
+ XLogRecPtr EndPos;
+ XLogRecPtr fpw_lsn;
+ XLogRecData *rdt;
+ XLogRecData *rdt_lastnormal;
+
+ /* info's high bits are reserved for use by me */
+ if (info & XLR_INFO_MASK)
+ elog(PANIC, "invalid xlog info mask %02X", info);
+
+ TRACE_POSTGRESQL_XLOG_INSERT(rmid, info);
+
+ /*
+ * In bootstrap mode, we don't actually log anything but XLOG resources;
+ * return a phony record pointer.
+ */
+ if (IsBootstrapProcessingMode() && rmid != RM_XLOG_ID)
+ {
+ EndPos = SizeOfXLogLongPHD; /* start of 1st chkpt record */
+ return EndPos;
+ }
+
+ /*
+ * Get values needed to decide whether to do full-page writes. Since we
+ * don't yet have an insertion lock, these could change under us, but
+ * XLogInsertRecord will recheck them once it has a lock.
+ */
+ GetFullPageWriteInfo(&RedoRecPtr, &doPageWrites);
+
+ /*
+ * Assemble an XLogRecData chain representing the WAL record, including
+ * any backup blocks needed.
+ *
+ * We may have to loop back to here if a race condition is detected in
+ * XLogInsertRecord. We could prevent the race by doing all this work
+ * while holding an insertion lock, but it seems better to avoid doing CRC
+ * calculations while holding one.
+ */
+retry:
+ rdt = XLogRecordAssemble(rmid, info, rdata, RedoRecPtr, doPageWrites,
+ &fpw_lsn, &rdt_lastnormal);
+
+ EndPos = XLogInsertRecord(rdt, fpw_lsn);
+
+ if (EndPos == InvalidXLogRecPtr)
+ {
+ /*
+ * Undo the changes we made to the rdata chain, and retry.
+ *
+ * XXX: This doesn't undo *all* the changes; the XLogRecData
+ * entries for buffers that we had already decided to back up have
+ * had their data-pointers cleared. That's OK, as long as we
+ * decide to back them up on the next iteration as well. Hence,
+ * don't allow "doPageWrites" value to go from true to false after
+ * we've modified the rdata chain.
+ */
+ bool newDoPageWrites;
+
+ GetFullPageWriteInfo(&RedoRecPtr, &newDoPageWrites);
+ doPageWrites = doPageWrites || newDoPageWrites;
+ rdt_lastnormal->next = NULL;
+
+ goto retry;
+ }
+
+ return EndPos;
+}
+
+/*
+ * Assemble a full WAL record, including backup blocks, from an XLogRecData
+ * chain, ready for insertion with XLogInsertRecord(). The record header
+ * fields are filled in, except for the xl_prev field and CRC.
+ *
+ * The rdata chain is modified, adding entries for full-page images.
+ * *rdt_lastnormal is set to point to the last normal (ie. not added by
+ * this function) entry. It can be used to reset the chain to its original
+ * state.
+ *
+ * If the rdata chain contains any buffer references, and a full-page image
+ * was not taken of all the buffers, *fpw_lsn is set to the lowest LSN among
+ * such pages. This signals that the assembled record is only good for
+ * insertion on the assumption that the RedoRecPtr and doPageWrites values
+ * were up-to-date.
+ */
+static XLogRecData *
+XLogRecordAssemble(RmgrId rmid, uint8 info, XLogRecData *rdata,
+ XLogRecPtr RedoRecPtr, bool doPageWrites,
+ XLogRecPtr *fpw_lsn, XLogRecData **rdt_lastnormal)
+{
+ bool isLogSwitch = (rmid == RM_XLOG_ID && info == XLOG_SWITCH);
+ XLogRecData *rdt;
+ Buffer dtbuf[XLR_MAX_BKP_BLOCKS];
+ bool dtbuf_bkp[XLR_MAX_BKP_BLOCKS];
+ uint32 len,
+ total_len;
+ unsigned i;
+
+ /*
+ * These need to be static because they are returned to the caller as part
+ * of the XLogRecData chain.
+ */
+ static BkpBlock dtbuf_xlg[XLR_MAX_BKP_BLOCKS];
+ static XLogRecData dtbuf_rdt1[XLR_MAX_BKP_BLOCKS];
+ static XLogRecData dtbuf_rdt2[XLR_MAX_BKP_BLOCKS];
+ static XLogRecData dtbuf_rdt3[XLR_MAX_BKP_BLOCKS];
+ static XLogRecData hdr_rdt;
+ static XLogRecord *rechdr;
+
+ if (rechdr == NULL)
+ {
+ static char rechdrbuf[SizeOfXLogRecord + MAXIMUM_ALIGNOF];
+
+ rechdr = (XLogRecord *) MAXALIGN(&rechdrbuf);
+ MemSet(rechdr, 0, SizeOfXLogRecord);
+ }
+
+ /* The record begins with the header */
+ hdr_rdt.data = (char *) rechdr;
+ hdr_rdt.len = SizeOfXLogRecord;
+ hdr_rdt.next = rdata;
+ total_len = SizeOfXLogRecord;
+
+ /*
+ * Here we scan the rdata chain, to determine which buffers must be backed
+ * up.
+ *
+ * We add entries for backup blocks to the chain, so that they don't need
+ * any special treatment in the critical section where the chunks are
+ * copied into the WAL buffers. Those entries have to be unlinked from the
+ * chain if we have to loop back here.
+ */
+ for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
+ {
+ dtbuf[i] = InvalidBuffer;
+ dtbuf_bkp[i] = false;
+ }
+
+ *fpw_lsn = InvalidXLogRecPtr;
+ len = 0;
+ for (rdt = rdata;;)
+ {
+ if (rdt->buffer == InvalidBuffer)
+ {
+ /* Simple data, just include it */
+ len += rdt->len;
+ }
+ else
+ {
+ /* Find info for buffer */
+ for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
+ {
+ if (rdt->buffer == dtbuf[i])
+ {
+ /* Buffer already referenced by earlier chain item */
+ if (dtbuf_bkp[i])
+ {
+ rdt->data = NULL;
+ rdt->len = 0;
+ }
+ else if (rdt->data)
+ len += rdt->len;
+ break;
+ }
+ if (dtbuf[i] == InvalidBuffer)
+ {
+ /* OK, put it in this slot */
+ XLogRecPtr page_lsn;
+ bool needs_backup;
+
+ dtbuf[i] = rdt->buffer;
+
+ /*
+ * Determine whether the buffer has to be backed up.
+ *
+ * We assume page LSN is first data on *every* page that
+ * can be passed to XLogInsert, whether it has the
+ * standard page layout or not. We don't need to take the
+ * buffer header lock for PageGetLSN because we hold an
+ * exclusive lock on the page and/or the relation.
+ */
+ page_lsn = PageGetLSN(BufferGetPage(rdt->buffer));
+ if (!doPageWrites)
+ needs_backup = false;
+ else if (page_lsn <= RedoRecPtr)
+ needs_backup = true;
+ else
+ needs_backup = false;
+
+ if (needs_backup)
+ {
+ /*
+ * The page needs to be backed up, so set up BkpBlock
+ */
+ XLogFillBkpBlock(rdt->buffer, rdt->buffer_std,
+ &(dtbuf_xlg[i]));
+ dtbuf_bkp[i] = true;
+ rdt->data = NULL;
+ rdt->len = 0;
+ }
+ else
+ {
+ if (rdt->data)
+ len += rdt->len;
+ if (*fpw_lsn == InvalidXLogRecPtr ||
+ page_lsn < *fpw_lsn)
+ {
+ *fpw_lsn = page_lsn;
+ }
+ }
+ break;
+ }
+ }
+ if (i >= XLR_MAX_BKP_BLOCKS)
+ elog(PANIC, "can backup at most %d blocks per xlog record",
+ XLR_MAX_BKP_BLOCKS);
+ }
+ /* Break out of loop when rdt points to last chain item */
+ if (rdt->next == NULL)
+ break;
+ rdt = rdt->next;
+ }
+ total_len += len;
+
+ /*
+ * Make additional rdata chain entries for the backup blocks, so that we
+ * don't need to special-case them in the write loop. This modifies the
+ * original rdata chain, but we keep a pointer to the last regular entry,
+ * rdt_lastnormal, so that we can undo this if we have to start over.
+ *
+ * At the exit of this loop, total_len includes the backup block data.
+ *
+ * Also set the appropriate info bits to show which buffers were backed
+ * up. The XLR_BKP_BLOCK(N) bit corresponds to the N'th distinct buffer
+ * value (ignoring InvalidBuffer) appearing in the rdata chain.
+ */
+ *rdt_lastnormal = rdt;
+ for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
+ {
+ BkpBlock *bkpb;
+ char *page;
+
+ if (!dtbuf_bkp[i])
+ continue;
+
+ info |= XLR_BKP_BLOCK(i);
+
+ bkpb = &(dtbuf_xlg[i]);
+ page = (char *) BufferGetBlock(dtbuf[i]);
+
+ rdt->next = &(dtbuf_rdt1[i]);
+ rdt = rdt->next;
+
+ rdt->data = (char *) bkpb;
+ rdt->len = sizeof(BkpBlock);
+ total_len += sizeof(BkpBlock);
+
+ rdt->next = &(dtbuf_rdt2[i]);
+ rdt = rdt->next;
+
+ if (bkpb->hole_length == 0)
+ {
+ rdt->data = page;
+ rdt->len = BLCKSZ;
+ total_len += BLCKSZ;
+ rdt->next = NULL;
+ }
+ else
+ {
+ /* must skip the hole */
+ rdt->data = page;
+ rdt->len = bkpb->hole_offset;
+ total_len += bkpb->hole_offset;
+
+ rdt->next = &(dtbuf_rdt3[i]);
+ rdt = rdt->next;
+
+ rdt->data = page + (bkpb->hole_offset + bkpb->hole_length);
+ rdt->len = BLCKSZ - (bkpb->hole_offset + bkpb->hole_length);
+ total_len += rdt->len;
+ rdt->next = NULL;
+ }
+ }
+
+ /*
+ * We disallow len == 0 because it provides a useful bit of extra error
+ * checking in ReadRecord. This means that all callers of XLogInsert
+ * must supply at least some not-in-a-buffer data. However, we make an
+ * exception for XLOG SWITCH records because we don't want them to ever
+ * cross a segment boundary.
+ */
+ if (len == 0 && !isLogSwitch)
+ elog(PANIC, "invalid xlog record length %u", rechdr->xl_len);
+
+ /*
+ * Fill in the fields in the record header. Prev-link is filled in later,
+ * once we know where in the WAL the record will be inserted. CRC is also
+ * not calculated yet.
+ */
+ rechdr->xl_xid = GetCurrentTransactionIdIfAny();
+ rechdr->xl_tot_len = total_len;
+ rechdr->xl_len = len; /* doesn't include backup blocks */
+ rechdr->xl_info = info;
+ rechdr->xl_rmid = rmid;
+ rechdr->xl_prev = InvalidXLogRecPtr;
+
+ return &hdr_rdt;
+}
+
+/*
+ * Determine whether the buffer referenced has to be backed up.
+ *
+ * Since we don't yet have the insert lock, fullPageWrites and forcePageWrites
+ * could change later, so the result should be used for optimization purposes
+ * only.
+ */
+bool
+XLogCheckBufferNeedsBackup(Buffer buffer)
+{
+ XLogRecPtr RedoRecPtr;
+ bool doPageWrites;
+ Page page;
+
+ GetFullPageWriteInfo(&RedoRecPtr, &doPageWrites);
+
+ page = BufferGetPage(buffer);
+
+ if (doPageWrites && PageGetLSN(page) <= RedoRecPtr)
+ return true; /* buffer requires backup */
+
+ return false; /* buffer does not need to be backed up */
+}
+
+/*
+ * Write a backup block if needed when we are setting a hint. Note that
+ * this may be called for a variety of page types, not just heaps.
+ *
+ * Callable while holding just share lock on the buffer content.
+ *
+ * We can't use the plain backup block mechanism since that relies on the
+ * Buffer being exclusively locked. Since some modifications (setting LSN, hint
+ * bits) are allowed in a sharelocked buffer that can lead to wal checksum
+ * failures. So instead we copy the page and insert the copied data as normal
+ * record data.
+ *
+ * We only need to do something if page has not yet been full page written in
+ * this checkpoint round. The LSN of the inserted wal record is returned if we
+ * had to write, InvalidXLogRecPtr otherwise.
+ *
+ * It is possible that multiple concurrent backends could attempt to write WAL
+ * records. In that case, multiple copies of the same block would be recorded
+ * in separate WAL records by different backends, though that is still OK from
+ * a correctness perspective.
+ */
+XLogRecPtr
+XLogSaveBufferForHint(Buffer buffer, bool buffer_std)
+{
+ XLogRecPtr recptr = InvalidXLogRecPtr;
+ XLogRecPtr lsn;
+ XLogRecPtr RedoRecPtr;
+
+ /*
+ * Ensure no checkpoint can change our view of RedoRecPtr.
+ */
+ Assert(MyPgXact->delayChkpt);
+
+ /*
+ * Update RedoRecPtr so that we can make the right decision
+ */
+ RedoRecPtr = GetRedoRecPtr();
+
+ /*
+ * We assume page LSN is first data on *every* page that can be passed to
+ * XLogInsert, whether it has the standard page layout or not. Since we're
+ * only holding a share-lock on the page, we must take the buffer header
+ * lock when we look at the LSN.
+ */
+ lsn = BufferGetLSNAtomic(buffer);
+
+ if (lsn <= RedoRecPtr)
+ {
+ XLogRecData rdata[2];
+ BkpBlock bkpb;
+ char copied_buffer[BLCKSZ];
+ char *origdata = (char *) BufferGetBlock(buffer);
+
+ /* Make a BkpBlock struct representing the buffer */
+ XLogFillBkpBlock(buffer, buffer_std, &bkpb);
+
+ /*
+ * Copy buffer so we don't have to worry about concurrent hint bit or
+ * lsn updates. We assume pd_lower/upper cannot be changed without an
+ * exclusive lock, so the contents bkp are not racy.
+ *
+ * With buffer_std set to false, XLogFillBkpBlock() sets hole_length
+ * and hole_offset to 0; so the following code is safe for either
+ * case.
+ */
+ memcpy(copied_buffer, origdata, bkpb.hole_offset);
+ memcpy(copied_buffer + bkpb.hole_offset,
+ origdata + bkpb.hole_offset + bkpb.hole_length,
+ BLCKSZ - bkpb.hole_offset - bkpb.hole_length);
+
+ /*
+ * Header for backup block.
+ */
+ rdata[0].data = (char *) &bkpb;
+ rdata[0].len = sizeof(BkpBlock);
+ rdata[0].buffer = InvalidBuffer;
+ rdata[0].next = &(rdata[1]);
+
+ /*
+ * Save copy of the buffer.
+ */
+ rdata[1].data = copied_buffer;
+ rdata[1].len = BLCKSZ - bkpb.hole_length;
+ rdata[1].buffer = InvalidBuffer;
+ rdata[1].next = NULL;
+
+ recptr = XLogInsert(RM_XLOG_ID, XLOG_FPI, rdata);
+ }
+
+ return recptr;
+}
+
+/*
+ * Write a WAL record containing a full image of a page. Caller is responsible
+ * for writing the page to disk after calling this routine.
+ *
+ * Note: If you're using this function, you should be building pages in private
+ * memory and writing them directly to smgr. If you're using buffers, call
+ * log_newpage_buffer instead.
+ *
+ * If the page follows the standard page layout, with a PageHeader and unused
+ * space between pd_lower and pd_upper, set 'page_std' to TRUE. That allows
+ * the unused space to be left out from the WAL record, making it smaller.
+ */
+XLogRecPtr
+log_newpage(RelFileNode *rnode, ForkNumber forkNum, BlockNumber blkno,
+ Page page, bool page_std)
+{
+ BkpBlock bkpb;
+ XLogRecPtr recptr;
+ XLogRecData rdata[3];
+
+ /* NO ELOG(ERROR) from here till newpage op is logged */
+ START_CRIT_SECTION();
+
+ bkpb.node = *rnode;
+ bkpb.fork = forkNum;
+ bkpb.block = blkno;
+
+ if (page_std)
+ {
+ /* Assume we can omit data between pd_lower and pd_upper */
+ uint16 lower = ((PageHeader) page)->pd_lower;
+ uint16 upper = ((PageHeader) page)->pd_upper;
+
+ if (lower >= SizeOfPageHeaderData &&
+ upper > lower &&
+ upper <= BLCKSZ)
+ {
+ bkpb.hole_offset = lower;
+ bkpb.hole_length = upper - lower;
+ }
+ else
+ {
+ /* No "hole" to compress out */
+ bkpb.hole_offset = 0;
+ bkpb.hole_length = 0;
+ }
+ }
+ else
+ {
+ /* Not a standard page header, don't try to eliminate "hole" */
+ bkpb.hole_offset = 0;
+ bkpb.hole_length = 0;
+ }
+
+ rdata[0].data = (char *) &bkpb;
+ rdata[0].len = sizeof(BkpBlock);
+ rdata[0].buffer = InvalidBuffer;
+ rdata[0].next = &(rdata[1]);
+
+ if (bkpb.hole_length == 0)
+ {
+ rdata[1].data = (char *) page;
+ rdata[1].len = BLCKSZ;
+ rdata[1].buffer = InvalidBuffer;
+ rdata[1].next = NULL;
+ }
+ else
+ {
+ /* must skip the hole */
+ rdata[1].data = (char *) page;
+ rdata[1].len = bkpb.hole_offset;
+ rdata[1].buffer = InvalidBuffer;
+ rdata[1].next = &rdata[2];
+
+ rdata[2].data = (char *) page + (bkpb.hole_offset + bkpb.hole_length);
+ rdata[2].len = BLCKSZ - (bkpb.hole_offset + bkpb.hole_length);
+ rdata[2].buffer = InvalidBuffer;
+ rdata[2].next = NULL;
+ }
+
+ recptr = XLogInsert(RM_XLOG_ID, XLOG_FPI, rdata);
+
+ /*
+ * The page may be uninitialized. If so, we can't set the LSN because that
+ * would corrupt the page.
+ */
+ if (!PageIsNew(page))
+ {
+ PageSetLSN(page, recptr);
+ }
+
+ END_CRIT_SECTION();
+
+ return recptr;
+}
+
+/*
+ * Write a WAL record containing a full image of a page.
+ *
+ * Caller should initialize the buffer and mark it dirty before calling this
+ * function. This function will set the page LSN.
+ *
+ * If the page follows the standard page layout, with a PageHeader and unused
+ * space between pd_lower and pd_upper, set 'page_std' to TRUE. That allows
+ * the unused space to be left out from the WAL record, making it smaller.
+ */
+XLogRecPtr
+log_newpage_buffer(Buffer buffer, bool page_std)
+{
+ Page page = BufferGetPage(buffer);
+ RelFileNode rnode;
+ ForkNumber forkNum;
+ BlockNumber blkno;
+
+ /* Shared buffers should be modified in a critical section. */
+ Assert(CritSectionCount > 0);
+
+ BufferGetTag(buffer, &rnode, &forkNum, &blkno);
+
+ return log_newpage(&rnode, forkNum, blkno, page, page_std);
+}
+
+/*
+ * Fill a BkpBlock for a buffer.
+ */
+static void
+XLogFillBkpBlock(Buffer buffer, bool buffer_std, BkpBlock *bkpb)
+{
+ BufferGetTag(buffer, &bkpb->node, &bkpb->fork, &bkpb->block);
+
+ if (buffer_std)
+ {
+ /* Assume we can omit data between pd_lower and pd_upper */
+ Page page = BufferGetPage(buffer);
+ uint16 lower = ((PageHeader) page)->pd_lower;
+ uint16 upper = ((PageHeader) page)->pd_upper;
+
+ if (lower >= SizeOfPageHeaderData &&
+ upper > lower &&
+ upper <= BLCKSZ)
+ {
+ bkpb->hole_offset = lower;
+ bkpb->hole_length = upper - lower;
+ }
+ else
+ {
+ /* No "hole" to compress out */
+ bkpb->hole_offset = 0;
+ bkpb->hole_length = 0;
+ }
+ }
+ else
+ {
+ /* Not a standard page header, don't try to eliminate "hole" */
+ bkpb->hole_offset = 0;
+ bkpb->hole_length = 0;
+ }
+}
#include "postgres.h"
#include "access/transam.h"
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
#include "access/xlog_internal.h"
#include "access/xlogreader.h"
#include "catalog/pg_control.h"
return buffer;
}
+/*
+ * Restore a full-page image from a backup block attached to an XLOG record.
+ *
+ * lsn: LSN of the XLOG record being replayed
+ * record: the complete XLOG record
+ * block_index: which backup block to restore (0 .. XLR_MAX_BKP_BLOCKS - 1)
+ * get_cleanup_lock: TRUE to get a cleanup rather than plain exclusive lock
+ * keep_buffer: TRUE to return the buffer still locked and pinned
+ *
+ * Returns the buffer number containing the page. Note this is not terribly
+ * useful unless keep_buffer is specified as TRUE.
+ *
+ * Note: when a backup block is available in XLOG, we restore it
+ * unconditionally, even if the page in the database appears newer.
+ * This is to protect ourselves against database pages that were partially
+ * or incorrectly written during a crash. We assume that the XLOG data
+ * must be good because it has passed a CRC check, while the database
+ * page might not be. This will force us to replay all subsequent
+ * modifications of the page that appear in XLOG, rather than possibly
+ * ignoring them as already applied, but that's not a huge drawback.
+ *
+ * If 'get_cleanup_lock' is true, a cleanup lock is obtained on the buffer,
+ * else a normal exclusive lock is used. During crash recovery, that's just
+ * pro forma because there can't be any regular backends in the system, but
+ * in hot standby mode the distinction is important.
+ *
+ * If 'keep_buffer' is true, return without releasing the buffer lock and pin;
+ * then caller is responsible for doing UnlockReleaseBuffer() later. This
+ * is needed in some cases when replaying XLOG records that touch multiple
+ * pages, to prevent inconsistent states from being visible to other backends.
+ * (Again, that's only important in hot standby mode.)
+ */
+Buffer
+RestoreBackupBlock(XLogRecPtr lsn, XLogRecord *record, int block_index,
+ bool get_cleanup_lock, bool keep_buffer)
+{
+ BkpBlock bkpb;
+ char *blk;
+ int i;
+
+ /* Locate requested BkpBlock in the record */
+ blk = (char *) XLogRecGetData(record) + record->xl_len;
+ for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
+ {
+ if (!(record->xl_info & XLR_BKP_BLOCK(i)))
+ continue;
+
+ memcpy(&bkpb, blk, sizeof(BkpBlock));
+ blk += sizeof(BkpBlock);
+
+ if (i == block_index)
+ {
+ /* Found it, apply the update */
+ return RestoreBackupBlockContents(lsn, bkpb, blk, get_cleanup_lock,
+ keep_buffer);
+ }
+
+ blk += BLCKSZ - bkpb.hole_length;
+ }
+
+ /* Caller specified a bogus block_index */
+ elog(ERROR, "failed to restore block_index %d", block_index);
+ return InvalidBuffer; /* keep compiler quiet */
+}
+
+/*
+ * Workhorse for RestoreBackupBlock usable without an xlog record
+ *
+ * Restores a full-page image from BkpBlock and a data pointer.
+ */
+Buffer
+RestoreBackupBlockContents(XLogRecPtr lsn, BkpBlock bkpb, char *blk,
+ bool get_cleanup_lock, bool keep_buffer)
+{
+ Buffer buffer;
+ Page page;
+
+ buffer = XLogReadBufferExtended(bkpb.node, bkpb.fork, bkpb.block,
+ RBM_ZERO);
+ Assert(BufferIsValid(buffer));
+ if (get_cleanup_lock)
+ LockBufferForCleanup(buffer);
+ else
+ LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
+
+ page = (Page) BufferGetPage(buffer);
+
+ if (bkpb.hole_length == 0)
+ {
+ memcpy((char *) page, blk, BLCKSZ);
+ }
+ else
+ {
+ memcpy((char *) page, blk, bkpb.hole_offset);
+ /* must zero-fill the hole */
+ MemSet((char *) page + bkpb.hole_offset, 0, bkpb.hole_length);
+ memcpy((char *) page + (bkpb.hole_offset + bkpb.hole_length),
+ blk + bkpb.hole_offset,
+ BLCKSZ - (bkpb.hole_offset + bkpb.hole_length));
+ }
+
+ /*
+ * The checksum value on this page is currently invalid. We don't need to
+ * reset it here since it will be set before being written.
+ */
+
+ /*
+ * The page may be uninitialized. If so, we can't set the LSN because that
+ * would corrupt the page.
+ */
+ if (!PageIsNew(page))
+ {
+ PageSetLSN(page, lsn);
+ }
+ MarkBufferDirty(buffer);
+
+ if (!keep_buffer)
+ UnlockReleaseBuffer(buffer);
+
+ return buffer;
+}
/*
* Struct actually returned by XLogFakeRelcacheEntry, though the declared
#include "access/sysattr.h"
#include "access/transam.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "catalog/binary_upgrade.h"
#include "catalog/catalog.h"
#include "catalog/dependency.h"
#include "access/htup_details.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "catalog/dependency.h"
#include "catalog/objectaccess.h"
#include "catalog/pg_authid.h"
#include "access/visibilitymap.h"
#include "access/xact.h"
+#include "access/xlog.h"
+#include "access/xloginsert.h"
#include "access/xlogutils.h"
#include "catalog/catalog.h"
#include "catalog/storage.h"
#include "access/transam.h"
#include "access/tuptoaster.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "catalog/catalog.h"
#include "catalog/dependency.h"
#include "catalog/heap.h"
#include "access/htup_details.h"
#include "access/sysattr.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "catalog/namespace.h"
#include "catalog/pg_type.h"
#include "commands/copy.h"
#include "access/htup_details.h"
#include "access/sysattr.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "catalog/toasting.h"
#include "commands/createas.h"
#include "commands/matview.h"
#include "access/heapam.h"
#include "access/htup_details.h"
#include "access/xact.h"
+#include "access/xloginsert.h"
#include "access/xlogutils.h"
#include "catalog/catalog.h"
#include "catalog/dependency.h"
#include "access/htup_details.h"
#include "access/multixact.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "catalog/catalog.h"
#include "catalog/indexing.h"
#include "catalog/namespace.h"
#include "access/htup_details.h"
#include "access/multixact.h"
#include "access/transam.h"
+#include "access/xlog.h"
+#include "access/xloginsert.h"
#include "access/xlogutils.h"
#include "catalog/dependency.h"
#include "catalog/namespace.h"
#include "access/relscan.h"
#include "access/sysattr.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "catalog/catalog.h"
#include "catalog/dependency.h"
#include "catalog/heap.h"
#include "access/htup_details.h"
#include "access/sysattr.h"
#include "access/xact.h"
+#include "access/xlog.h"
+#include "access/xloginsert.h"
#include "catalog/catalog.h"
#include "catalog/dependency.h"
#include "catalog/indexing.h"
#include "access/multixact.h"
#include "access/transam.h"
#include "access/visibilitymap.h"
+#include "access/xlog.h"
#include "catalog/catalog.h"
#include "catalog/storage.h"
#include "commands/dbcommands.h"
#include "access/htup_details.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "catalog/pg_authid.h"
#include "commands/variable.h"
#include "miscadmin.h"
#include <sys/file.h>
#include <unistd.h>
+#include "access/xlog.h"
#include "catalog/catalog.h"
#include "catalog/storage.h"
#include "executor/instrument.h"
#include "miscadmin.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "catalog/catalog.h"
#include "catalog/pg_tablespace.h"
#include "pgstat.h"
#include "access/clog.h"
#include "access/subtrans.h"
#include "access/transam.h"
-#include "access/xact.h"
#include "access/twophase.h"
+#include "access/xact.h"
+#include "access/xlog.h"
#include "catalog/catalog.h"
#include "miscadmin.h"
#include "storage/proc.h"
#include "access/twophase.h"
#include "access/xact.h"
#include "access/xlog.h"
+#include "access/xloginsert.h"
#include "miscadmin.h"
#include "storage/bufmgr.h"
#include "storage/lmgr.h"
#include "access/transam.h"
#include "access/twophase.h"
#include "access/twophase_rmgr.h"
+#include "access/xlog.h"
#include "miscadmin.h"
#include "pg_trace.h"
#include "pgstat.h"
#include "access/twophase.h"
#include "access/twophase_rmgr.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "miscadmin.h"
#include "storage/bufmgr.h"
#include "storage/predicate.h"
#include "access/reloptions.h"
#include "access/twophase.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "catalog/catalog.h"
#include "catalog/namespace.h"
#include "catalog/toasting.h"
#include "access/transam.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "funcapi.h"
#include "miscadmin.h"
#include "libpq/pqformat.h"
#include "access/sysattr.h"
#include "access/transam.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "catalog/catalog.h"
#include "catalog/index.h"
#include "catalog/indexing.h"
#include <unistd.h>
#include "access/xact.h"
+#include "access/xlog.h"
+#include "access/xloginsert.h"
#include "catalog/catalog.h"
#include "catalog/pg_tablespace.h"
#include "catalog/storage.h"
#include "access/htup_details.h"
#include "access/sysattr.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "catalog/catalog.h"
#include "catalog/indexing.h"
#include "catalog/namespace.h"
#include "postgres.h"
+#include <limits.h>
+
#include "access/htup_details.h"
#include "commands/tablespace.h"
#include "executor/executor.h"
#include "access/subtrans.h"
#include "access/transam.h"
#include "access/xact.h"
+#include "access/xlog.h"
#include "storage/bufmgr.h"
#include "storage/procarray.h"
#include "utils/builtins.h"
#include "access/transam.h"
#include "access/tuptoaster.h"
#include "access/multixact.h"
+#include "access/xlog.h"
#include "access/xlog_internal.h"
#include "catalog/catversion.h"
#include "catalog/pg_control.h"
#ifndef CLOG_H
#define CLOG_H
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
+#include "lib/stringinfo.h"
/*
* Possible transaction statuses --- note that all-zeroes is the initial
#ifndef GIN_H
#define GIN_H
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
+#include "lib/stringinfo.h"
#include "storage/block.h"
#include "utils/relcache.h"
#include "access/genam.h"
#include "access/gin.h"
#include "access/itup.h"
+#include "access/xloginsert.h"
#include "fmgr.h"
#include "storage/bufmgr.h"
#include "utils/rbtree.h"
#include "access/gist.h"
#include "access/itup.h"
+#include "access/xlogrecord.h"
#include "fmgr.h"
#include "storage/bufmgr.h"
#include "storage/buffile.h"
#include "access/genam.h"
#include "access/itup.h"
#include "access/sdir.h"
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
#include "fmgr.h"
+#include "lib/stringinfo.h"
#include "storage/bufmgr.h"
#include "storage/lock.h"
#include "utils/relcache.h"
#define HEAPAM_XLOG_H
#include "access/htup.h"
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
+#include "lib/stringinfo.h"
+#include "storage/buf.h"
#include "storage/bufpage.h"
#include "storage/relfilenode.h"
#include "utils/relcache.h"
#ifndef MULTIXACT_H
#define MULTIXACT_H
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
+#include "lib/stringinfo.h"
/*
#include "access/genam.h"
#include "access/itup.h"
#include "access/sdir.h"
-#include "access/xlog.h"
-#include "access/xlogutils.h"
+#include "access/xlogrecord.h"
#include "catalog/pg_index.h"
+#include "lib/stringinfo.h"
+#include "storage/bufmgr.h"
/* There's room for a 16-bit vacuum cycle ID in BTPageOpaqueData */
typedef uint16 BTCycleId;
#define SPGIST_H
#include "access/skey.h"
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
#include "fmgr.h"
+#include "lib/stringinfo.h"
/* reloption parameters */
#include "access/itup.h"
#include "access/spgist.h"
#include "nodes/tidbitmap.h"
+#include "storage/buf.h"
#include "storage/relfilenode.h"
#include "utils/relcache.h"
#ifndef XACT_H
#define XACT_H
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
+#include "lib/stringinfo.h"
#include "nodes/pg_list.h"
#include "storage/relfilenode.h"
+#include "utils/datetime.h"
/*
#include "access/rmgr.h"
#include "access/xlogdefs.h"
+#include "access/xloginsert.h"
+#include "access/xlogrecord.h"
#include "datatype/timestamp.h"
#include "lib/stringinfo.h"
-#include "storage/block.h"
-#include "storage/buf.h"
-#include "storage/relfilenode.h"
-#include "utils/pg_crc.h"
-/*
- * The overall layout of an XLOG record is:
- * Fixed-size header (XLogRecord struct)
- * rmgr-specific data
- * BkpBlock
- * backup block data
- * BkpBlock
- * backup block data
- * ...
- *
- * where there can be zero to four backup blocks (as signaled by xl_info flag
- * bits). XLogRecord structs always start on MAXALIGN boundaries in the WAL
- * files, and we round up SizeOfXLogRecord so that the rmgr data is also
- * guaranteed to begin on a MAXALIGN boundary. However, no padding is added
- * to align BkpBlock structs or backup block data.
- *
- * NOTE: xl_len counts only the rmgr data, not the XLogRecord header,
- * and also not any backup blocks. xl_tot_len counts everything. Neither
- * length field is rounded up to an alignment boundary.
- */
-typedef struct XLogRecord
-{
- uint32 xl_tot_len; /* total len of entire record */
- TransactionId xl_xid; /* xact id */
- uint32 xl_len; /* total len of rmgr data */
- uint8 xl_info; /* flag bits, see below */
- RmgrId xl_rmid; /* resource manager for this record */
- /* 2 bytes of padding here, initialize to zero */
- XLogRecPtr xl_prev; /* ptr to previous record in log */
- pg_crc32 xl_crc; /* CRC for this record */
-
- /* If MAXALIGN==8, there are 4 wasted bytes here */
-
- /* ACTUAL LOG DATA FOLLOWS AT END OF STRUCT */
-
-} XLogRecord;
-
-#define SizeOfXLogRecord MAXALIGN(sizeof(XLogRecord))
-
-#define XLogRecGetData(record) ((char*) (record) + SizeOfXLogRecord)
-
-/*
- * XLOG uses only low 4 bits of xl_info. High 4 bits may be used by rmgr.
- */
-#define XLR_INFO_MASK 0x0F
-
-/*
- * If we backed up any disk blocks with the XLOG record, we use flag bits in
- * xl_info to signal it. We support backup of up to 4 disk blocks per XLOG
- * record.
- */
-#define XLR_BKP_BLOCK_MASK 0x0F /* all info bits used for bkp blocks */
-#define XLR_MAX_BKP_BLOCKS 4
-#define XLR_BKP_BLOCK(iblk) (0x08 >> (iblk)) /* iblk in 0..3 */
/* Sync methods */
#define SYNC_METHOD_FSYNC 0
#define SYNC_METHOD_OPEN_DSYNC 4 /* for O_DSYNC */
extern int sync_method;
-/*
- * The rmgr data to be written by XLogInsert() is defined by a chain of
- * one or more XLogRecData structs. (Multiple structs would be used when
- * parts of the source data aren't physically adjacent in memory, or when
- * multiple associated buffers need to be specified.)
- *
- * If buffer is valid then XLOG will check if buffer must be backed up
- * (ie, whether this is first change of that page since last checkpoint).
- * If so, the whole page contents are attached to the XLOG record, and XLOG
- * sets XLR_BKP_BLOCK(N) bit in xl_info. Note that the buffer must be pinned
- * and exclusive-locked by the caller, so that it won't change under us.
- * NB: when the buffer is backed up, we DO NOT insert the data pointed to by
- * this XLogRecData struct into the XLOG record, since we assume it's present
- * in the buffer. Therefore, rmgr redo routines MUST pay attention to
- * XLR_BKP_BLOCK(N) to know what is actually stored in the XLOG record.
- * The N'th XLR_BKP_BLOCK bit corresponds to the N'th distinct buffer
- * value (ignoring InvalidBuffer) appearing in the rdata chain.
- *
- * When buffer is valid, caller must set buffer_std to indicate whether the
- * page uses standard pd_lower/pd_upper header fields. If this is true, then
- * XLOG is allowed to omit the free space between pd_lower and pd_upper from
- * the backed-up page image. Note that even when buffer_std is false, the
- * page MUST have an LSN field as its first eight bytes!
- *
- * Note: data can be NULL to indicate no rmgr data associated with this chain
- * entry. This can be sensible (ie, not a wasted entry) if buffer is valid.
- * The implication is that the buffer has been changed by the operation being
- * logged, and so may need to be backed up, but the change can be redone using
- * only information already present elsewhere in the XLOG entry.
- */
-typedef struct XLogRecData
-{
- char *data; /* start of rmgr data to include */
- uint32 len; /* length of rmgr data to include */
- Buffer buffer; /* buffer associated with data, if any */
- bool buffer_std; /* buffer has standard pd_lower/pd_upper */
- struct XLogRecData *next; /* next struct in chain, or NULL */
-} XLogRecData;
-
extern PGDLLIMPORT TimeLineID ThisTimeLineID; /* current TLI */
/*
extern CheckpointStatsData CheckpointStats;
-extern XLogRecPtr XLogInsert(RmgrId rmid, uint8 info, XLogRecData *rdata);
-extern bool XLogCheckBufferNeedsBackup(Buffer buffer);
+extern XLogRecPtr XLogInsertRecord(XLogRecData *rdata, XLogRecPtr fpw_lsn);
extern void XLogFlush(XLogRecPtr RecPtr);
extern bool XLogBackgroundFlush(void);
extern bool XLogNeedsFlush(XLogRecPtr RecPtr);
extern int XLogFileInit(XLogSegNo segno, bool *use_existent, bool use_lock);
extern int XLogFileOpen(XLogSegNo segno);
-extern XLogRecPtr log_newpage(RelFileNode *rnode, ForkNumber forkNum,
- BlockNumber blk, char *page, bool page_std);
-extern XLogRecPtr log_newpage_buffer(Buffer buffer, bool page_std);
-extern XLogRecPtr XLogSaveBufferForHint(Buffer buffer, bool buffer_std);
-
extern void CheckXLogRemoved(XLogSegNo segno, TimeLineID tli);
extern XLogSegNo XLogGetLastRemovedSegno(void);
extern void XLogSetAsyncXactLSN(XLogRecPtr record);
extern void XLogSetReplicationSlotMinimumLSN(XLogRecPtr lsn);
-extern Buffer RestoreBackupBlock(XLogRecPtr lsn, XLogRecord *record,
- int block_index,
- bool get_cleanup_lock, bool keep_buffer);
-
extern void xlog_redo(XLogRecPtr lsn, XLogRecord *record);
extern void xlog_desc(StringInfo buf, XLogRecord *record);
extern const char *xlog_identify(uint8 info);
extern void XLogPutNextOid(Oid nextOid);
extern XLogRecPtr XLogRestorePoint(const char *rpName);
extern void UpdateFullPageWrites(void);
+extern void GetFullPageWriteInfo(XLogRecPtr *RedoRecPtr_p, bool *doPageWrites_p);
extern XLogRecPtr GetRedoRecPtr(void);
extern XLogRecPtr GetInsertRecPtr(void);
extern XLogRecPtr GetFlushRecPtr(void);
* NOTE: this file is intended to contain declarations useful for
* manipulating the XLOG files directly, but it is not supposed to be
* needed by rmgr routines (redo support for individual record types).
- * So the XLogRecord typedef and associated stuff appear in xlog.h.
+ * So the XLogRecord typedef and associated stuff appear in xlogrecord.h.
*
* Note: This file must be includable in both frontend and backend contexts,
* to allow stand-alone tools like pg_receivexlog to deal with WAL files.
#define XLOG_INTERNAL_H
#include "access/xlogdefs.h"
+#include "access/xlogrecord.h"
#include "datatype/timestamp.h"
#include "lib/stringinfo.h"
#include "pgtime.h"
#include "storage/relfilenode.h"
-/*
- * Header info for a backup block appended to an XLOG record.
- *
- * As a trivial form of data compression, the XLOG code is aware that
- * PG data pages usually contain an unused "hole" in the middle, which
- * contains only zero bytes. If hole_length > 0 then we have removed
- * such a "hole" from the stored data (and it's not counted in the
- * XLOG record's CRC, either). Hence, the amount of block data actually
- * present following the BkpBlock struct is BLCKSZ - hole_length bytes.
- *
- * Note that we don't attempt to align either the BkpBlock struct or the
- * block's data. So, the struct must be copied to aligned local storage
- * before use.
- */
-typedef struct BkpBlock
-{
- RelFileNode node; /* relation containing block */
- ForkNumber fork; /* fork within the relation */
- BlockNumber block; /* block number */
- uint16 hole_offset; /* number of bytes before "hole" */
- uint16 hole_length; /* number of bytes in "hole" */
-
- /* ACTUAL BLOCK DATA FOLLOWS AT END OF STRUCT */
-} BkpBlock;
-
/*
* Each page of XLOG file has a header like this:
*/
TimeLineID PrevTimeLineID; /* previous TLI we forked off from */
} xl_end_of_recovery;
-/*
- * XLogRecord is defined in xlog.h, but we avoid #including that to keep
- * this file includable in stand-alone programs.
- */
-struct XLogRecord;
-
/*
* Method table for resource managers.
*
typedef struct RmgrData
{
const char *rm_name;
- void (*rm_redo) (XLogRecPtr lsn, struct XLogRecord *rptr);
- void (*rm_desc) (StringInfo buf, struct XLogRecord *rptr);
+ void (*rm_redo) (XLogRecPtr lsn, XLogRecord *rptr);
+ void (*rm_desc) (StringInfo buf, XLogRecord *rptr);
const char *(*rm_identify) (uint8 info);
void (*rm_startup) (void);
void (*rm_cleanup) (void);
--- /dev/null
+/*
+ * xloginsert.h
+ *
+ * Functions for generating WAL records
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/access/xloginsert.h
+ */
+#ifndef XLOGINSERT_H
+#define XLOGINSERT_H
+
+#include "access/rmgr.h"
+#include "access/xlogdefs.h"
+#include "storage/block.h"
+#include "storage/buf.h"
+#include "storage/relfilenode.h"
+
+/*
+ * The rmgr data to be written by XLogInsert() is defined by a chain of
+ * one or more XLogRecData structs. (Multiple structs would be used when
+ * parts of the source data aren't physically adjacent in memory, or when
+ * multiple associated buffers need to be specified.)
+ *
+ * If buffer is valid then XLOG will check if buffer must be backed up
+ * (ie, whether this is first change of that page since last checkpoint).
+ * If so, the whole page contents are attached to the XLOG record, and XLOG
+ * sets XLR_BKP_BLOCK(N) bit in xl_info. Note that the buffer must be pinned
+ * and exclusive-locked by the caller, so that it won't change under us.
+ * NB: when the buffer is backed up, we DO NOT insert the data pointed to by
+ * this XLogRecData struct into the XLOG record, since we assume it's present
+ * in the buffer. Therefore, rmgr redo routines MUST pay attention to
+ * XLR_BKP_BLOCK(N) to know what is actually stored in the XLOG record.
+ * The N'th XLR_BKP_BLOCK bit corresponds to the N'th distinct buffer
+ * value (ignoring InvalidBuffer) appearing in the rdata chain.
+ *
+ * When buffer is valid, caller must set buffer_std to indicate whether the
+ * page uses standard pd_lower/pd_upper header fields. If this is true, then
+ * XLOG is allowed to omit the free space between pd_lower and pd_upper from
+ * the backed-up page image. Note that even when buffer_std is false, the
+ * page MUST have an LSN field as its first eight bytes!
+ *
+ * Note: data can be NULL to indicate no rmgr data associated with this chain
+ * entry. This can be sensible (ie, not a wasted entry) if buffer is valid.
+ * The implication is that the buffer has been changed by the operation being
+ * logged, and so may need to be backed up, but the change can be redone using
+ * only information already present elsewhere in the XLOG entry.
+ */
+typedef struct XLogRecData
+{
+ char *data; /* start of rmgr data to include */
+ uint32 len; /* length of rmgr data to include */
+ Buffer buffer; /* buffer associated with data, if any */
+ bool buffer_std; /* buffer has standard pd_lower/pd_upper */
+ struct XLogRecData *next; /* next struct in chain, or NULL */
+} XLogRecData;
+
+extern XLogRecPtr XLogInsert(RmgrId rmid, uint8 info, XLogRecData *rdata);
+extern XLogRecPtr log_newpage(RelFileNode *rnode, ForkNumber forkNum,
+ BlockNumber blk, char *page, bool page_std);
+extern XLogRecPtr log_newpage_buffer(Buffer buffer, bool page_std);
+extern XLogRecPtr XLogSaveBufferForHint(Buffer buffer, bool buffer_std);
+extern bool XLogCheckBufferNeedsBackup(Buffer buffer);
+
+#endif /* XLOGINSERT_H */
--- /dev/null
+/*
+ * xlogrecord.h
+ *
+ * Definitions for the WAL record format.
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/access/xlogrecord.h
+ */
+#ifndef XLOGRECORD_H
+#define XLOGRECORD_H
+
+#include "access/rmgr.h"
+#include "access/xlogdefs.h"
+#include "storage/block.h"
+#include "storage/relfilenode.h"
+#include "utils/pg_crc.h"
+
+/*
+ * The overall layout of an XLOG record is:
+ * Fixed-size header (XLogRecord struct)
+ * rmgr-specific data
+ * BkpBlock
+ * backup block data
+ * BkpBlock
+ * backup block data
+ * ...
+ *
+ * where there can be zero to four backup blocks (as signaled by xl_info flag
+ * bits). XLogRecord structs always start on MAXALIGN boundaries in the WAL
+ * files, and we round up SizeOfXLogRecord so that the rmgr data is also
+ * guaranteed to begin on a MAXALIGN boundary. However, no padding is added
+ * to align BkpBlock structs or backup block data.
+ *
+ * NOTE: xl_len counts only the rmgr data, not the XLogRecord header,
+ * and also not any backup blocks. xl_tot_len counts everything. Neither
+ * length field is rounded up to an alignment boundary.
+ */
+typedef struct XLogRecord
+{
+ uint32 xl_tot_len; /* total len of entire record */
+ TransactionId xl_xid; /* xact id */
+ uint32 xl_len; /* total len of rmgr data */
+ uint8 xl_info; /* flag bits, see below */
+ RmgrId xl_rmid; /* resource manager for this record */
+ /* 2 bytes of padding here, initialize to zero */
+ XLogRecPtr xl_prev; /* ptr to previous record in log */
+ pg_crc32 xl_crc; /* CRC for this record */
+
+ /* If MAXALIGN==8, there are 4 wasted bytes here */
+
+ /* ACTUAL LOG DATA FOLLOWS AT END OF STRUCT */
+
+} XLogRecord;
+
+#define SizeOfXLogRecord MAXALIGN(sizeof(XLogRecord))
+
+#define XLogRecGetData(record) ((char*) (record) + SizeOfXLogRecord)
+
+/*
+ * XLOG uses only low 4 bits of xl_info. High 4 bits may be used by rmgr.
+ */
+#define XLR_INFO_MASK 0x0F
+
+/*
+ * If we backed up any disk blocks with the XLOG record, we use flag bits in
+ * xl_info to signal it. We support backup of up to 4 disk blocks per XLOG
+ * record.
+ */
+#define XLR_BKP_BLOCK_MASK 0x0F /* all info bits used for bkp blocks */
+#define XLR_MAX_BKP_BLOCKS 4
+#define XLR_BKP_BLOCK(iblk) (0x08 >> (iblk)) /* iblk in 0..3 */
+
+/*
+ * Header info for a backup block appended to an XLOG record.
+ *
+ * As a trivial form of data compression, the XLOG code is aware that
+ * PG data pages usually contain an unused "hole" in the middle, which
+ * contains only zero bytes. If hole_length > 0 then we have removed
+ * such a "hole" from the stored data (and it's not counted in the
+ * XLOG record's CRC, either). Hence, the amount of block data actually
+ * present following the BkpBlock struct is BLCKSZ - hole_length bytes.
+ *
+ * Note that we don't attempt to align either the BkpBlock struct or the
+ * block's data. So, the struct must be copied to aligned local storage
+ * before use.
+ */
+typedef struct BkpBlock
+{
+ RelFileNode node; /* relation containing block */
+ ForkNumber fork; /* fork within the relation */
+ BlockNumber block; /* block number */
+ uint16 hole_offset; /* number of bytes before "hole" */
+ uint16 hole_length; /* number of bytes in "hole" */
+
+ /* ACTUAL BLOCK DATA FOLLOWS AT END OF STRUCT */
+} BkpBlock;
+
+#endif /* XLOGRECORD_H */
#ifndef XLOG_UTILS_H
#define XLOG_UTILS_H
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
#include "storage/bufmgr.h"
extern Buffer XLogReadBufferExtended(RelFileNode rnode, ForkNumber forknum,
BlockNumber blkno, ReadBufferMode mode);
+extern Buffer RestoreBackupBlock(XLogRecPtr lsn, XLogRecord *record,
+ int block_index,
+ bool get_cleanup_lock, bool keep_buffer);
+extern Buffer RestoreBackupBlockContents(XLogRecPtr lsn, BkpBlock bkpb,
+ char *blk, bool get_cleanup_lock, bool keep_buffer);
+
extern Relation CreateFakeRelcacheEntry(RelFileNode rnode);
extern void FreeFakeRelcacheEntry(Relation fakerel);
#ifndef STORAGE_XLOG_H
#define STORAGE_XLOG_H
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
+#include "lib/stringinfo.h"
#include "storage/block.h"
#include "storage/relfilenode.h"
#ifndef DBCOMMANDS_H
#define DBCOMMANDS_H
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
+#include "lib/stringinfo.h"
#include "nodes/parsenodes.h"
/* XLOG stuff */
#ifndef SEQUENCE_H
#define SEQUENCE_H
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
#include "fmgr.h"
+#include "lib/stringinfo.h"
#include "nodes/parsenodes.h"
#include "storage/relfilenode.h"
#ifndef TABLESPACE_H
#define TABLESPACE_H
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
+#include "lib/stringinfo.h"
#include "nodes/parsenodes.h"
/* XLOG stuff */
#define DECODE_H
#include "access/xlogreader.h"
+#include "access/xlogrecord.h"
#include "replication/reorderbuffer.h"
#include "replication/logical.h"
#ifndef STANDBY_H
#define STANDBY_H
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
+#include "lib/stringinfo.h"
#include "storage/lock.h"
#include "storage/procsignal.h"
#include "storage/relfilenode.h"
#ifndef RELMAPPER_H
#define RELMAPPER_H
-#include "access/xlog.h"
+#include "access/xlogrecord.h"
+#include "lib/stringinfo.h"
/* ----------------
* relmap-related XLOG entries
projects / users / gsingh / postgres.git / commitdiff