pg_query 2.2.1 → 4.2.0

data/ext/pg_query/include/access/xlogreader.h

@@ -3,7 +3,7 @@
  * xlogreader.h
  *		Definitions for the generic XLog reading facility
  *
- * Portions Copyright (c) 2013-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 2013-2022, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
  *		src/include/access/xlogreader.h
@@ -17,7 +17,7 @@
  *		XLogBeginRead() or XLogFindNextRecord(), and call XLogReadRecord()
  *		until it returns NULL.
  *
- *		Callers supply a page_read callback if they want to to call
+ *		Callers supply a page_read callback if they want to call
  *		XLogReadRecord or XLogFindNextRecord; it can be passed in as NULL
  *		otherwise.  The WALRead function can be used as a helper to write
  *		page_read callbacks, but it is not mandatory; callers that use it,
@@ -39,6 +39,7 @@
 #endif
 
 #include "access/xlogrecord.h"
+#include "storage/buf.h"
 
 /* WALOpenSegment represents a WAL segment being read. */
 typedef struct WALOpenSegment
@@ -125,6 +126,9 @@ typedef struct
 	ForkNumber	forknum;
 	BlockNumber blkno;
 
+	/* Prefetching workspace. */
+	Buffer		prefetch_buffer;
+
 	/* copy of the fork_flags field from the XLogRecordBlockHeader */
 	uint8		flags;
 
@@ -144,6 +148,30 @@ typedef struct
 	uint16		data_bufsz;
 } DecodedBkpBlock;
 
+/*
+ * The decoded contents of a record.  This occupies a contiguous region of
+ * memory, with main_data and blocks[n].data pointing to memory after the
+ * members declared here.
+ */
+typedef struct DecodedXLogRecord
+{
+	/* Private member used for resource management. */
+	size_t		size;			/* total size of decoded record */
+	bool		oversized;		/* outside the regular decode buffer? */
+	struct DecodedXLogRecord *next; /* decoded record queue link */
+
+	/* Public members. */
+	XLogRecPtr	lsn;			/* location */
+	XLogRecPtr	next_lsn;		/* location of next record */
+	XLogRecord	header;			/* header */
+	RepOriginId record_origin;
+	TransactionId toplevel_xid; /* XID of top-level transaction */
+	char	   *main_data;		/* record's main data portion */
+	uint32		main_data_len;	/* main data portion's length */
+	int			max_block_id;	/* highest block_id in use (-1 if none) */
+	DecodedBkpBlock blocks[FLEXIBLE_ARRAY_MEMBER];
+} DecodedXLogRecord;
+
 struct XLogReaderState
 {
 	/*
@@ -171,10 +199,23 @@ struct XLogReaderState
 	 * Start and end point of last record read.  EndRecPtr is also used as the
 	 * position to read next.  Calling XLogBeginRead() sets EndRecPtr to the
 	 * starting position and ReadRecPtr to invalid.
+	 *
+	 * Start and end point of last record returned by XLogReadRecord().  These
+	 * are also available as record->lsn and record->next_lsn.
 	 */
 	XLogRecPtr	ReadRecPtr;		/* start of last record read */
 	XLogRecPtr	EndRecPtr;		/* end+1 of last record read */
 
+	/*
+	 * Set at the end of recovery: the start point of a partial record at the
+	 * end of WAL (InvalidXLogRecPtr if there wasn't one), and the start
+	 * location of its first contrecord that went missing.
+	 */
+	XLogRecPtr	abortedRecPtr;
+	XLogRecPtr	missingContrecPtr;
+	/* Set when XLP_FIRST_IS_OVERWRITE_CONTRECORD is found */
+	XLogRecPtr	overwrittenRecPtr;
+
 
 	/* ----------------------------------------
 	 * Decoded representation of current record
@@ -182,25 +223,43 @@ struct XLogReaderState
 	 * Use XLogRecGet* functions to investigate the record; these fields
 	 * should not be accessed directly.
 	 * ----------------------------------------
+	 * Start and end point of the last record read and decoded by
+	 * XLogReadRecordInternal().  NextRecPtr is also used as the position to
+	 * decode next.  Calling XLogBeginRead() sets NextRecPtr and EndRecPtr to
+	 * the requested starting position.
 	 */
-	XLogRecord *decoded_record; /* currently decoded record */
+	XLogRecPtr	DecodeRecPtr;	/* start of last record decoded */
+	XLogRecPtr	NextRecPtr;		/* end+1 of last record decoded */
+	XLogRecPtr	PrevRecPtr;		/* start of previous record decoded */
 
-	char	   *main_data;		/* record's main data portion */
-	uint32		main_data_len;	/* main data portion's length */
-	uint32		main_data_bufsz;	/* allocated size of the buffer */
-
-	RepOriginId record_origin;
-
-	/* information about blocks referenced by the record. */
-	DecodedBkpBlock blocks[XLR_MAX_BLOCK_ID + 1];
-
-	int			max_block_id;	/* highest block_id in use (-1 if none) */
+	/* Last record returned by XLogReadRecord(). */
+	DecodedXLogRecord *record;
 
 	/* ----------------------------------------
 	 * private/internal state
 	 * ----------------------------------------
 	 */
 
+	/*
+	 * Buffer for decoded records.  This is a circular buffer, though
+	 * individual records can't be split in the middle, so some space is often
+	 * wasted at the end.  Oversized records that don't fit in this space are
+	 * allocated separately.
+	 */
+	char	   *decode_buffer;
+	size_t		decode_buffer_size;
+	bool		free_decode_buffer; /* need to free? */
+	char	   *decode_buffer_head; /* data is read from the head */
+	char	   *decode_buffer_tail; /* new data is written at the tail */
+
+	/*
+	 * Queue of records that have been decoded.  This is a linked list that
+	 * usually consists of consecutive records in decode_buffer, but may also
+	 * contain oversized records allocated with palloc().
+	 */
+	DecodedXLogRecord *decode_queue_head;	/* oldest decoded record */
+	DecodedXLogRecord *decode_queue_tail;	/* newest decoded record */
+
 	/*
 	 * Buffer for currently read page (XLOG_BLCKSZ bytes, valid up to at least
 	 * readLen bytes)
@@ -250,18 +309,24 @@ struct XLogReaderState
 
 	/* Buffer to hold error message */
 	char	   *errormsg_buf;
+	bool		errormsg_deferred;
 
 	/*
-	 * Set at the end of recovery: the start point of a partial record at the
-	 * end of WAL (InvalidXLogRecPtr if there wasn't one), and the start
-	 * location of its first contrecord that went missing.
+	 * Flag to indicate to XLogPageReadCB that it should not block waiting for
+	 * data.
 	 */
-	XLogRecPtr	abortedRecPtr;
-	XLogRecPtr	missingContrecPtr;
-	/* Set when XLP_FIRST_IS_OVERWRITE_CONTRECORD is found */
-	XLogRecPtr	overwrittenRecPtr;
+	bool		nonblocking;
 };
 
+/*
+ * Check if XLogNextRecord() has any more queued records or an error to return.
+ */
+static inline bool
+XLogReaderHasQueuedRecordOrError(XLogReaderState *state)
+{
+	return (state->decode_queue_head != NULL) || state->errormsg_deferred;
+}
+
 /* Get a new XLogReader */
 extern XLogReaderState *XLogReaderAllocate(int wal_segment_size,
 										   const char *waldir,
@@ -272,20 +337,45 @@ extern XLogReaderRoutine *LocalXLogReaderRoutine(void);
 /* Free an XLogReader */
 extern void XLogReaderFree(XLogReaderState *state);
 
+/* Optionally provide a circular decoding buffer to allow readahead. */
+extern void XLogReaderSetDecodeBuffer(XLogReaderState *state,
+									  void *buffer,
+									  size_t size);
+
 /* Position the XLogReader to given record */
 extern void XLogBeginRead(XLogReaderState *state, XLogRecPtr RecPtr);
-#ifdef FRONTEND
 extern XLogRecPtr XLogFindNextRecord(XLogReaderState *state, XLogRecPtr RecPtr);
-#endif							/* FRONTEND */
+
+/* Return values from XLogPageReadCB. */
+typedef enum XLogPageReadResult
+{
+	XLREAD_SUCCESS = 0,			/* record is successfully read */
+	XLREAD_FAIL = -1,			/* failed during reading a record */
+	XLREAD_WOULDBLOCK = -2		/* nonblocking mode only, no data */
+} XLogPageReadResult;
 
 /* Read the next XLog record. Returns NULL on end-of-WAL or failure */
 extern struct XLogRecord *XLogReadRecord(XLogReaderState *state,
 										 char **errormsg);
 
+/* Consume the next record or error. */
+extern DecodedXLogRecord *XLogNextRecord(XLogReaderState *state,
+										 char **errormsg);
+
+/* Release the previously returned record, if necessary. */
+extern XLogRecPtr XLogReleasePreviousRecord(XLogReaderState *state);
+
+/* Try to read ahead, if there is data and space. */
+extern DecodedXLogRecord *XLogReadAhead(XLogReaderState *state,
+										bool nonblocking);
+
 /* Validate a page */
 extern bool XLogReaderValidatePageHeader(XLogReaderState *state,
 										 XLogRecPtr recptr, char *phdr);
 
+/* Forget error produced by XLogReaderValidatePageHeader(). */
+extern void XLogReaderResetError(XLogReaderState *state);
+
 /*
  * Error information from WALRead that both backend and frontend caller can
  * process.  Currently only errors from pg_pread can be reported.
@@ -305,24 +395,36 @@ extern bool WALRead(XLogReaderState *state,
 
 /* Functions for decoding an XLogRecord */
 
-extern bool DecodeXLogRecord(XLogReaderState *state, XLogRecord *record,
+extern size_t DecodeXLogRecordRequiredSpace(size_t xl_tot_len);
+extern bool DecodeXLogRecord(XLogReaderState *state,
+							 DecodedXLogRecord *decoded,
+							 XLogRecord *record,
+							 XLogRecPtr lsn,
 							 char **errmsg);
 
-#define XLogRecGetTotalLen(decoder) ((decoder)->decoded_record->xl_tot_len)
-#define XLogRecGetPrev(decoder) ((decoder)->decoded_record->xl_prev)
-#define XLogRecGetInfo(decoder) ((decoder)->decoded_record->xl_info)
-#define XLogRecGetRmid(decoder) ((decoder)->decoded_record->xl_rmid)
-#define XLogRecGetXid(decoder) ((decoder)->decoded_record->xl_xid)
-#define XLogRecGetOrigin(decoder) ((decoder)->record_origin)
-#define XLogRecGetData(decoder) ((decoder)->main_data)
-#define XLogRecGetDataLen(decoder) ((decoder)->main_data_len)
-#define XLogRecHasAnyBlockRefs(decoder) ((decoder)->max_block_id >= 0)
-#define XLogRecHasBlockRef(decoder, block_id) \
-	((decoder)->blocks[block_id].in_use)
-#define XLogRecHasBlockImage(decoder, block_id) \
-	((decoder)->blocks[block_id].has_image)
-#define XLogRecBlockImageApply(decoder, block_id) \
-	((decoder)->blocks[block_id].apply_image)
+/*
+ * Macros that provide access to parts of the record most recently returned by
+ * XLogReadRecord() or XLogNextRecord().
+ */
+#define XLogRecGetTotalLen(decoder) ((decoder)->record->header.xl_tot_len)
+#define XLogRecGetPrev(decoder) ((decoder)->record->header.xl_prev)
+#define XLogRecGetInfo(decoder) ((decoder)->record->header.xl_info)
+#define XLogRecGetRmid(decoder) ((decoder)->record->header.xl_rmid)
+#define XLogRecGetXid(decoder) ((decoder)->record->header.xl_xid)
+#define XLogRecGetOrigin(decoder) ((decoder)->record->record_origin)
+#define XLogRecGetTopXid(decoder) ((decoder)->record->toplevel_xid)
+#define XLogRecGetData(decoder) ((decoder)->record->main_data)
+#define XLogRecGetDataLen(decoder) ((decoder)->record->main_data_len)
+#define XLogRecHasAnyBlockRefs(decoder) ((decoder)->record->max_block_id >= 0)
+#define XLogRecMaxBlockId(decoder) ((decoder)->record->max_block_id)
+#define XLogRecGetBlock(decoder, i) (&(decoder)->record->blocks[(i)])
+#define XLogRecHasBlockRef(decoder, block_id)			\
+	(((decoder)->record->max_block_id >= (block_id)) &&	\
+	 ((decoder)->record->blocks[block_id].in_use))
+#define XLogRecHasBlockImage(decoder, block_id)		\
+	((decoder)->record->blocks[block_id].has_image)
+#define XLogRecBlockImageApply(decoder, block_id)		\
+	((decoder)->record->blocks[block_id].apply_image)
 
 #ifndef FRONTEND
 extern FullTransactionId XLogRecGetFullXid(XLogReaderState *record);
@@ -330,8 +432,12 @@ extern FullTransactionId XLogRecGetFullXid(XLogReaderState *record);
 
 extern bool RestoreBlockImage(XLogReaderState *record, uint8 block_id, char *page);
 extern char *XLogRecGetBlockData(XLogReaderState *record, uint8 block_id, Size *len);
-extern bool XLogRecGetBlockTag(XLogReaderState *record, uint8 block_id,
+extern void XLogRecGetBlockTag(XLogReaderState *record, uint8 block_id,
 							   RelFileNode *rnode, ForkNumber *forknum,
 							   BlockNumber *blknum);
+extern bool XLogRecGetBlockTagExtended(XLogReaderState *record, uint8 block_id,
+									   RelFileNode *rnode, ForkNumber *forknum,
+									   BlockNumber *blknum,
+									   Buffer *prefetch_buffer);
 
 #endif							/* XLOGREADER_H */

data/ext/pg_query/include/access/xlogrecord.h

@@ -3,7 +3,7 @@
  *
  * Definitions for the WAL record format.
  *
- * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * src/include/access/xlogrecord.h
@@ -114,8 +114,8 @@ typedef struct XLogRecordBlockHeader
  * present is (BLCKSZ - <length of "hole" bytes>).
  *
  * Additionally, when wal_compression is enabled, we will try to compress full
- * page images using the PGLZ compression algorithm, after removing the "hole".
- * This can reduce the WAL volume, but at some extra cost of CPU spent
+ * page images using one of the supported algorithms, after removing the
+ * "hole". This can reduce the WAL volume, but at some extra cost of CPU spent
  * on the compression during WAL logging. In this case, since the "hole"
  * length cannot be calculated by subtracting the number of page image bytes
  * from BLCKSZ, basically it needs to be stored as an extra information.
@@ -134,7 +134,7 @@ typedef struct XLogRecordBlockImageHeader
 	uint8		bimg_info;		/* flag bits, see below */
 
 	/*
-	 * If BKPIMAGE_HAS_HOLE and BKPIMAGE_IS_COMPRESSED, an
+	 * If BKPIMAGE_HAS_HOLE and BKPIMAGE_COMPRESSED(), an
 	 * XLogRecordBlockCompressHeader struct follows.
 	 */
 } XLogRecordBlockImageHeader;
@@ -144,9 +144,16 @@ typedef struct XLogRecordBlockImageHeader
 
 /* Information stored in bimg_info */
 #define BKPIMAGE_HAS_HOLE		0x01	/* page image has "hole" */
-#define BKPIMAGE_IS_COMPRESSED		0x02	/* page image is compressed */
-#define BKPIMAGE_APPLY		0x04	/* page image should be restored during
-									 * replay */
+#define BKPIMAGE_APPLY			0x02	/* page image should be restored
+										 * during replay */
+/* compression methods supported */
+#define BKPIMAGE_COMPRESS_PGLZ	0x04
+#define BKPIMAGE_COMPRESS_LZ4	0x08
+#define BKPIMAGE_COMPRESS_ZSTD	0x10
+
+#define	BKPIMAGE_COMPRESSED(info) \
+	((info & (BKPIMAGE_COMPRESS_PGLZ | BKPIMAGE_COMPRESS_LZ4 | \
+			  BKPIMAGE_COMPRESS_ZSTD)) != 0)
 
 /*
  * Extra header information used when page image has "hole" and
@@ -211,8 +218,9 @@ typedef struct XLogRecordDataHeaderLong
  * Block IDs used to distinguish different kinds of record fragments. Block
  * references are numbered from 0 to XLR_MAX_BLOCK_ID. A rmgr is free to use
  * any ID number in that range (although you should stick to small numbers,
- * because the WAL machinery is optimized for that case). A couple of ID
- * numbers are reserved to denote the "main" data portion of the record.
+ * because the WAL machinery is optimized for that case). A few ID
+ * numbers are reserved to denote the "main" data portion of the record,
+ * as well as replication-supporting transaction metadata.
  *
  * The maximum is currently set at 32, quite arbitrarily. Most records only
  * need a handful of block references, but there are a few exceptions that
@@ -223,5 +231,6 @@ typedef struct XLogRecordDataHeaderLong
 #define XLR_BLOCK_ID_DATA_SHORT		255
 #define XLR_BLOCK_ID_DATA_LONG		254
 #define XLR_BLOCK_ID_ORIGIN			253
+#define XLR_BLOCK_ID_TOPLEVEL_XID	252
 
 #endif							/* XLOGRECORD_H */

data/ext/pg_query/include/access/xlogrecovery.h

@@ -0,0 +1,157 @@
+/*
+ * xlogrecovery.h
+ *
+ * Functions for WAL recovery and standby mode
+ *
+ * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/access/xlogrecovery.h
+ */
+#ifndef XLOGRECOVERY_H
+#define XLOGRECOVERY_H
+
+#include "access/xlogreader.h"
+#include "catalog/pg_control.h"
+#include "lib/stringinfo.h"
+#include "utils/timestamp.h"
+
+/*
+ * Recovery target type.
+ * Only set during a Point in Time recovery, not when in standby mode.
+ */
+typedef enum
+{
+	RECOVERY_TARGET_UNSET,
+	RECOVERY_TARGET_XID,
+	RECOVERY_TARGET_TIME,
+	RECOVERY_TARGET_NAME,
+	RECOVERY_TARGET_LSN,
+	RECOVERY_TARGET_IMMEDIATE
+} RecoveryTargetType;
+
+/*
+ * Recovery target TimeLine goal
+ */
+typedef enum
+{
+	RECOVERY_TARGET_TIMELINE_CONTROLFILE,
+	RECOVERY_TARGET_TIMELINE_LATEST,
+	RECOVERY_TARGET_TIMELINE_NUMERIC
+} RecoveryTargetTimeLineGoal;
+
+/* Recovery pause states */
+typedef enum RecoveryPauseState
+{
+	RECOVERY_NOT_PAUSED,		/* pause not requested */
+	RECOVERY_PAUSE_REQUESTED,	/* pause requested, but not yet paused */
+	RECOVERY_PAUSED				/* recovery is paused */
+} RecoveryPauseState;
+
+/* User-settable GUC parameters */
+extern PGDLLIMPORT bool recoveryTargetInclusive;
+extern PGDLLIMPORT int recoveryTargetAction;
+extern PGDLLIMPORT int recovery_min_apply_delay;
+extern PGDLLIMPORT char *PrimaryConnInfo;
+extern PGDLLIMPORT char *PrimarySlotName;
+extern PGDLLIMPORT char *recoveryRestoreCommand;
+extern PGDLLIMPORT char *recoveryEndCommand;
+extern PGDLLIMPORT char *archiveCleanupCommand;
+
+/* indirectly set via GUC system */
+extern PGDLLIMPORT TransactionId recoveryTargetXid;
+extern PGDLLIMPORT char *recovery_target_time_string;
+extern PGDLLIMPORT TimestampTz recoveryTargetTime;
+extern PGDLLIMPORT const char *recoveryTargetName;
+extern PGDLLIMPORT XLogRecPtr recoveryTargetLSN;
+extern PGDLLIMPORT RecoveryTargetType recoveryTarget;
+extern PGDLLIMPORT char *PromoteTriggerFile;
+extern PGDLLIMPORT bool wal_receiver_create_temp_slot;
+extern PGDLLIMPORT RecoveryTargetTimeLineGoal recoveryTargetTimeLineGoal;
+extern PGDLLIMPORT TimeLineID recoveryTargetTLIRequested;
+extern PGDLLIMPORT TimeLineID recoveryTargetTLI;
+
+/* Have we already reached a consistent database state? */
+extern PGDLLIMPORT bool reachedConsistency;
+
+/* Are we currently in standby mode? */
+extern PGDLLIMPORT bool StandbyMode;
+
+extern Size XLogRecoveryShmemSize(void);
+extern void XLogRecoveryShmemInit(void);
+
+extern void InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdownPtr, bool *haveBackupLabel, bool *haveTblspcMap);
+extern void PerformWalRecovery(void);
+
+/*
+ * FinishWalRecovery() returns this.  It contains information about the point
+ * where recovery ended, and why it ended.
+ */
+typedef struct
+{
+	/*
+	 * Information about the last valid or applied record, after which new WAL
+	 * can be appended.  'lastRec' is the position where the last record
+	 * starts, and 'endOfLog' is its end.  'lastPage' is a copy of the last
+	 * partial page that contains endOfLog (or NULL if endOfLog is exactly at
+	 * page boundary).  'lastPageBeginPtr' is the position where the last page
+	 * begins.
+	 *
+	 * endOfLogTLI is the TLI in the filename of the XLOG segment containing
+	 * the last applied record.  It could be different from lastRecTLI, if
+	 * there was a timeline switch in that segment, and we were reading the
+	 * old WAL from a segment belonging to a higher timeline.
+	 */
+	XLogRecPtr	lastRec;		/* start of last valid or applied record */
+	TimeLineID	lastRecTLI;
+	XLogRecPtr	endOfLog;		/* end of last valid or applied record */
+	TimeLineID	endOfLogTLI;
+
+	XLogRecPtr	lastPageBeginPtr;	/* LSN of page that contains endOfLog */
+	char	   *lastPage;		/* copy of the last page, up to endOfLog */
+
+	/*
+	 * abortedRecPtr is the start pointer of a broken record at end of WAL
+	 * when recovery completes; missingContrecPtr is the location of the first
+	 * contrecord that went missing.  See CreateOverwriteContrecordRecord for
+	 * details.
+	 */
+	XLogRecPtr	abortedRecPtr;
+	XLogRecPtr	missingContrecPtr;
+
+	/* short human-readable string describing why recovery ended */
+	char	   *recoveryStopReason;
+
+	/*
+	 * If standby or recovery signal file was found, these flags are set
+	 * accordingly.
+	 */
+	bool		standby_signal_file_found;
+	bool		recovery_signal_file_found;
+} EndOfWalRecoveryInfo;
+
+extern EndOfWalRecoveryInfo *FinishWalRecovery(void);
+extern void ShutdownWalRecovery(void);
+extern void RemovePromoteSignalFiles(void);
+
+extern bool HotStandbyActive(void);
+extern XLogRecPtr GetXLogReplayRecPtr(TimeLineID *replayTLI);
+extern RecoveryPauseState GetRecoveryPauseState(void);
+extern void SetRecoveryPause(bool recoveryPause);
+extern void GetXLogReceiptTime(TimestampTz *rtime, bool *fromStream);
+extern TimestampTz GetLatestXTime(void);
+extern TimestampTz GetCurrentChunkReplayStartTime(void);
+extern XLogRecPtr GetCurrentReplayRecPtr(TimeLineID *replayEndTLI);
+
+extern bool PromoteIsTriggered(void);
+extern bool CheckPromoteSignal(void);
+extern void WakeupRecovery(void);
+
+extern void StartupRequestWalReceiverRestart(void);
+extern void XLogRequestWalReceiverReply(void);
+
+extern void RecoveryRequiresIntParameter(const char *param_name, int currValue, int minValue);
+
+extern void xlog_outdesc(StringInfo buf, XLogReaderState *record);
+
+#endif							/* XLOGRECOVERY_H */