Use pg_pread() and pg_pwrite() for data files and WAL.

Cut down on system calls by doing random I/O using offset-based OS
routines where available.  Remove the code for tracking the 'virtual'
seek position.  The only reason left to call FileSeek() was to get
the file's size, so provide a new function FileSize() instead.

Author: Oskari Saarenmaa, Thomas Munro
Reviewed-by: Thomas Munro, Jesper Pedersen, Tom Lane, Alvaro Herrera
Discussion: https://postgr.es/m/CAEepm=02rapCpPR3ZGF2vW=SBHSdFYO_bz_f-wwWJonmA3APgw@mail.gmail.com
Discussion: https://postgr.es/m/b8748d39-0b19-0514-a1b9-4e5a28e6a208%40gmail.com
Discussion: https://postgr.es/m/a86bd200-ebbe-d829-e3ca-0c4474b2fcb7%40ohmu.fi

src/backend/access/heap/rewriteheap.c

@@ -935,7 +935,7 @@ logical_heap_rewrite_flush_mappings(RewriteState state)
 		 * Note that we deviate from the usual WAL coding practices here,
 		 * check the above "Logical rewrite support" comment for reasoning.
 		 */
-		written = FileWrite(src->vfd, waldata_start, len,
+		written = FileWrite(src->vfd, waldata_start, len, src->off,
 							WAIT_EVENT_LOGICAL_REWRITE_WRITE);
 		if (written != len)
 			ereport(ERROR,

src/backend/access/transam/xlog.c

@@ -2478,18 +2478,6 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible)
 			Size		nleft;
 			int			written;
 
-			/* Need to seek in the file? */
-			if (openLogOff != startoffset)
-			{
-				if (lseek(openLogFile, (off_t) startoffset, SEEK_SET) < 0)
-					ereport(PANIC,
-							(errcode_for_file_access(),
-							 errmsg("could not seek in log file %s to offset %u: %m",
-									XLogFileNameP(ThisTimeLineID, openLogSegNo),
-									startoffset)));
-				openLogOff = startoffset;
-			}
-
 			/* OK to write the page(s) */
 			from = XLogCtl->pages + startidx * (Size) XLOG_BLCKSZ;
 			nbytes = npages * (Size) XLOG_BLCKSZ;
@@ -2498,7 +2486,7 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible)
 			{
 				errno = 0;
 				pgstat_report_wait_start(WAIT_EVENT_WAL_WRITE);
-				written = write(openLogFile, from, nleft);
+				written = pg_pwrite(openLogFile, from, nleft, startoffset);
 				pgstat_report_wait_end();
 				if (written <= 0)
 				{
@@ -2513,6 +2501,7 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible)
 				}
 				nleft -= written;
 				from += written;
+				startoffset += written;
 			} while (nleft > 0);
 
 			/* Update state for write */
@@ -11821,22 +11810,9 @@ retry:
 
 	/* Read the requested page */
 	readOff = targetPageOff;
-	if (lseek(readFile, (off_t) readOff, SEEK_SET) < 0)
-	{
-		char		fname[MAXFNAMELEN];
-		int			save_errno = errno;
-
-		XLogFileName(fname, curFileTLI, readSegNo, wal_segment_size);
-		errno = save_errno;
-		ereport(emode_for_corrupt_record(emode, targetPagePtr + reqLen),
-				(errcode_for_file_access(),
-				 errmsg("could not seek in log segment %s to offset %u: %m",
-						fname, readOff)));
-		goto next_record_is_invalid;
-	}
 
 	pgstat_report_wait_start(WAIT_EVENT_WAL_READ);
-	r = read(readFile, readBuf, XLOG_BLCKSZ);
+	r = pg_pread(readFile, readBuf, XLOG_BLCKSZ, (off_t) readOff);
 	if (r != XLOG_BLCKSZ)
 	{
 		char		fname[MAXFNAMELEN];

src/backend/storage/file/buffile.c

@@ -67,12 +67,6 @@ struct BufFile
 	int			numFiles;		/* number of physical files in set */
 	/* all files except the last have length exactly MAX_PHYSICAL_FILESIZE */
 	File	   *files;			/* palloc'd array with numFiles entries */
-	off_t	   *offsets;		/* palloc'd array with numFiles entries */
-
-	/*
-	 * offsets[i] is the current seek position of files[i].  We use this to
-	 * avoid making redundant FileSeek calls.
-	 */
 
 	bool		isInterXact;	/* keep open over transactions? */
 	bool		dirty;			/* does buffer need to be written? */
@@ -116,7 +110,6 @@ makeBufFileCommon(int nfiles)
 	BufFile    *file = (BufFile *) palloc(sizeof(BufFile));
 
 	file->numFiles = nfiles;
-	file->offsets = (off_t *) palloc0(sizeof(off_t) * nfiles);
 	file->isInterXact = false;
 	file->dirty = false;
 	file->resowner = CurrentResourceOwner;
@@ -170,10 +163,7 @@ extendBufFile(BufFile *file)
 
 	file->files = (File *) repalloc(file->files,
 									(file->numFiles + 1) * sizeof(File));
-	file->offsets = (off_t *) repalloc(file->offsets,
-									   (file->numFiles + 1) * sizeof(off_t));
 	file->files[file->numFiles] = pfile;
-	file->offsets[file->numFiles] = 0L;
 	file->numFiles++;
 }
 
@@ -396,7 +386,6 @@ BufFileClose(BufFile *file)
 		FileClose(file->files[i]);
 	/* release the buffer space */
 	pfree(file->files);
-	pfree(file->offsets);
 	pfree(file);
 }
 
@@ -422,27 +411,17 @@ BufFileLoadBuffer(BufFile *file)
 		file->curOffset = 0L;
 	}
 
-	/*
-	 * May need to reposition physical file.
-	 */
-	thisfile = file->files[file->curFile];
-	if (file->curOffset != file->offsets[file->curFile])
-	{
-		if (FileSeek(thisfile, file->curOffset, SEEK_SET) != file->curOffset)
-			return;				/* seek failed, read nothing */
-		file->offsets[file->curFile] = file->curOffset;
-	}
-
 	/*
 	 * Read whatever we can get, up to a full bufferload.
 	 */
+	thisfile = file->files[file->curFile];
 	file->nbytes = FileRead(thisfile,
 							file->buffer.data,
 							sizeof(file->buffer),
+							file->curOffset,
 							WAIT_EVENT_BUFFILE_READ);
 	if (file->nbytes < 0)
 		file->nbytes = 0;
-	file->offsets[file->curFile] += file->nbytes;
 	/* we choose not to advance curOffset here */
 
 	if (file->nbytes > 0)
@@ -491,23 +470,14 @@ BufFileDumpBuffer(BufFile *file)
 		if ((off_t) bytestowrite > availbytes)
 			bytestowrite = (int) availbytes;
 
-		/*
-		 * May need to reposition physical file.
-		 */
 		thisfile = file->files[file->curFile];
-		if (file->curOffset != file->offsets[file->curFile])
-		{
-			if (FileSeek(thisfile, file->curOffset, SEEK_SET) != file->curOffset)
-				return;			/* seek failed, give up */
-			file->offsets[file->curFile] = file->curOffset;
-		}
 		bytestowrite = FileWrite(thisfile,
 								 file->buffer.data + wpos,
 								 bytestowrite,
+								 file->curOffset,
 								 WAIT_EVENT_BUFFILE_WRITE);
 		if (bytestowrite <= 0)
 			return;				/* failed to write */
-		file->offsets[file->curFile] += bytestowrite;
 		file->curOffset += bytestowrite;
 		wpos += bytestowrite;
 
@@ -803,11 +773,10 @@ BufFileSize(BufFile *file)
 {
 	off_t		lastFileSize;
 
-	/* Get the size of the last physical file by seeking to end. */
-	lastFileSize = FileSeek(file->files[file->numFiles - 1], 0, SEEK_END);
+	/* Get the size of the last physical file. */
+	lastFileSize = FileSize(file->files[file->numFiles - 1]);
 	if (lastFileSize < 0)
 		return -1;
-	file->offsets[file->numFiles - 1] = lastFileSize;
 
 	return ((file->numFiles - 1) * (off_t) MAX_PHYSICAL_FILESIZE) +
 		lastFileSize;
@@ -849,13 +818,8 @@ BufFileAppend(BufFile *target, BufFile *source)
 
 	target->files = (File *)
 		repalloc(target->files, sizeof(File) * newNumFiles);
-	target->offsets = (off_t *)
-		repalloc(target->offsets, sizeof(off_t) * newNumFiles);
 	for (i = target->numFiles; i < newNumFiles; i++)
-	{
 		target->files[i] = source->files[i - target->numFiles];
-		target->offsets[i] = source->offsets[i - target->numFiles];
-	}
 	target->numFiles = newNumFiles;
 
 	return startBlock;

src/backend/storage/smgr/md.c

@@ -522,22 +522,7 @@ mdextend(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 
 	Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
 
-	/*
-	 * Note: because caller usually obtained blocknum by calling mdnblocks,
-	 * which did a seek(SEEK_END), this seek is often redundant and will be
-	 * optimized away by fd.c.  It's not redundant, however, if there is a
-	 * partial page at the end of the file. In that case we want to try to
-	 * overwrite the partial page with a full page.  It's also not redundant
-	 * if bufmgr.c had to dump another buffer of the same file to make room
-	 * for the new page's buffer.
-	 */
-	if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
-		ereport(ERROR,
-				(errcode_for_file_access(),
-				 errmsg("could not seek to block %u in file \"%s\": %m",
-						blocknum, FilePathName(v->mdfd_vfd))));
-
-	if ((nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, WAIT_EVENT_DATA_FILE_EXTEND)) != BLCKSZ)
+	if ((nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, seekpos, WAIT_EVENT_DATA_FILE_EXTEND)) != BLCKSZ)
 	{
 		if (nbytes < 0)
 			ereport(ERROR,
@@ -748,13 +733,7 @@ mdread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 
 	Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
 
-	if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
-		ereport(ERROR,
-				(errcode_for_file_access(),
-				 errmsg("could not seek to block %u in file \"%s\": %m",
-						blocknum, FilePathName(v->mdfd_vfd))));
-
-	nbytes = FileRead(v->mdfd_vfd, buffer, BLCKSZ, WAIT_EVENT_DATA_FILE_READ);
+	nbytes = FileRead(v->mdfd_vfd, buffer, BLCKSZ, seekpos, WAIT_EVENT_DATA_FILE_READ);
 
 	TRACE_POSTGRESQL_SMGR_MD_READ_DONE(forknum, blocknum,
 									   reln->smgr_rnode.node.spcNode,
@@ -824,13 +803,7 @@ mdwrite(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 
 	Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
 
-	if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
-		ereport(ERROR,
-				(errcode_for_file_access(),
-				 errmsg("could not seek to block %u in file \"%s\": %m",
-						blocknum, FilePathName(v->mdfd_vfd))));
-
-	nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, WAIT_EVENT_DATA_FILE_WRITE);
+	nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, seekpos, WAIT_EVENT_DATA_FILE_WRITE);
 
 	TRACE_POSTGRESQL_SMGR_MD_WRITE_DONE(forknum, blocknum,
 										reln->smgr_rnode.node.spcNode,
@@ -1979,7 +1952,7 @@ _mdnblocks(SMgrRelation reln, ForkNumber forknum, MdfdVec *seg)
 {
 	off_t		len;
 
-	len = FileSeek(seg->mdfd_vfd, 0L, SEEK_END);
+	len = FileSize(seg->mdfd_vfd);
 	if (len < 0)
 		ereport(ERROR,
 				(errcode_for_file_access(),

src/include/storage/fd.h

@@ -15,7 +15,7 @@
 /*
  * calls:
  *
- *	File {Close, Read, Write, Seek, Tell, Sync}
+ *	File {Close, Read, Write, Size, Sync}
  *	{Path Name Open, Allocate, Free} File
  *
  * These are NOT JUST RENAMINGS OF THE UNIX ROUTINES.
@@ -42,10 +42,6 @@
 #include <dirent.h>
 
 
-/*
- * FileSeek uses the standard UNIX lseek(2) flags.
- */
-
 typedef int File;
 
 
@@ -68,10 +64,10 @@ extern File PathNameOpenFilePerm(const char *fileName, int fileFlags, mode_t fil
 extern File OpenTemporaryFile(bool interXact);
 extern void FileClose(File file);
 extern int	FilePrefetch(File file, off_t offset, int amount, uint32 wait_event_info);
-extern int	FileRead(File file, char *buffer, int amount, uint32 wait_event_info);
-extern int	FileWrite(File file, char *buffer, int amount, uint32 wait_event_info);
+extern int	FileRead(File file, char *buffer, int amount, off_t offset, uint32 wait_event_info);
+extern int	FileWrite(File file, char *buffer, int amount, off_t offset, uint32 wait_event_info);
 extern int	FileSync(File file, uint32 wait_event_info);
-extern off_t FileSeek(File file, off_t offset, int whence);
+extern off_t FileSize(File file);
 extern int	FileTruncate(File file, off_t offset, uint32 wait_event_info);
 extern void FileWriteback(File file, off_t offset, off_t nbytes, uint32 wait_event_info);
 extern char *FilePathName(File file);