Provide vectored variants of FileRead() and FileWrite().

macdice · macdice · commit 871fe4917e1e · 2023-12-12T13:12:43.000+13:00
FileReadV() and FileWriteV() adapt pg_preadv() and pg_pwritev() for fd.c's virtual file descriptors. The simple FileRead() and FileWrite() functions are now implemented in terms of the vectored functions, to avoid code duplication, and they are converted back to the corresponding simple system calls further down (commit 15c9ac3). Later work will make more interesting multi-iovec calls. The traditional behavior of reporting a "fake" ENOSPC error is simplified. It's now always set for non-failing writes, for the benefit of callers that expect to log a meaningful "%m" if they determine that the write was short. (Perhaps we should consider getting rid of that expectation one day.) Reviewed-by: Heikki Linnakangas <hlinnaka@iki.fi> Discussion: https://postgr.es/m/CA+hUKGJkOiOCa+mag4BF+zHo7qo=o9CFheB8=g6uT5TUm2gkvA@mail.gmail.com
diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c
@@ -2110,18 +2110,18 @@ FileWriteback(File file, off_t offset, off_t nbytes, uint32 wait_event_info)
 }
 
 int
-FileRead(File file, void *buffer, size_t amount, off_t offset,
-		 uint32 wait_event_info)
+FileReadV(File file, const struct iovec *iov, int iovcnt, off_t offset,
+		  uint32 wait_event_info)
 {
 	int			returnCode;
 	Vfd		   *vfdP;
 
 	Assert(FileIsValid(file));
 
-	DO_DB(elog(LOG, "FileRead: %d (%s) " INT64_FORMAT " %zu %p",
+	DO_DB(elog(LOG, "FileReadV: %d (%s) " INT64_FORMAT " %d",
 			   file, VfdCache[file].fileName,
 			   (int64) offset,
-			   amount, buffer));
+			   iovcnt));
 
 	returnCode = FileAccess(file);
 	if (returnCode < 0)
@@ -2131,7 +2131,7 @@ FileRead(File file, void *buffer, size_t amount, off_t offset,
 
 retry:
 	pgstat_report_wait_start(wait_event_info);
-	returnCode = pg_pread(vfdP->fd, buffer, amount, offset);
+	returnCode = pg_preadv(vfdP->fd, iov, iovcnt, offset);
 	pgstat_report_wait_end();
 
 	if (returnCode < 0)
@@ -2166,18 +2166,18 @@ FileRead(File file, void *buffer, size_t amount, off_t offset,
 }
 
 int
-FileWrite(File file, const void *buffer, size_t amount, off_t offset,
-		  uint32 wait_event_info)
+FileWriteV(File file, const struct iovec *iov, int iovcnt, off_t offset,
+		   uint32 wait_event_info)
 {
 	int			returnCode;
 	Vfd		   *vfdP;
 
 	Assert(FileIsValid(file));
 
-	DO_DB(elog(LOG, "FileWrite: %d (%s) " INT64_FORMAT " %zu %p",
+	DO_DB(elog(LOG, "FileWriteV: %d (%s) " INT64_FORMAT " %d",
 			   file, VfdCache[file].fileName,
 			   (int64) offset,
-			   amount, buffer));
+			   iovcnt));
 
 	returnCode = FileAccess(file);
 	if (returnCode < 0)
@@ -2195,7 +2195,10 @@ FileWrite(File file, const void *buffer, size_t amount, off_t offset,
 	 */
 	if (temp_file_limit >= 0 && (vfdP->fdstate & FD_TEMP_FILE_LIMIT))
 	{
-		off_t		past_write = offset + amount;
+		off_t		past_write = offset;
+
+		for (int i = 0; i < iovcnt; ++i)
+			past_write += iov[i].iov_len;
 
 		if (past_write > vfdP->fileSize)
 		{
@@ -2211,23 +2214,27 @@ FileWrite(File file, const void *buffer, size_t amount, off_t offset,
 	}
 
 retry:
-	errno = 0;
 	pgstat_report_wait_start(wait_event_info);
-	returnCode = pg_pwrite(VfdCache[file].fd, buffer, amount, offset);
+	returnCode = pg_pwritev(vfdP->fd, iov, iovcnt, offset);
 	pgstat_report_wait_end();
 
-	/* if write didn't set errno, assume problem is no disk space */
-	if (returnCode != amount && errno == 0)
-		errno = ENOSPC;
-
 	if (returnCode >= 0)
 	{
+		/*
+		 * Some callers expect short writes to set errno, and traditionally we
+		 * have assumed that they imply disk space shortage.  We don't want to
+		 * waste CPU cycles adding up the total size here, so we'll just set
+		 * it for all successful writes in case such a caller determines that
+		 * the write was short and ereports "%m".
+		 */
+		errno = ENOSPC;
+
 		/*
 		 * Maintain fileSize and temporary_files_size if it's a temp file.
 		 */
 		if (vfdP->fdstate & FD_TEMP_FILE_LIMIT)
 		{
-			off_t		past_write = offset + amount;
+			off_t		past_write = offset + returnCode;
 
 			if (past_write > vfdP->fileSize)
 			{
@@ -2239,7 +2246,7 @@ FileWrite(File file, const void *buffer, size_t amount, off_t offset,
 	else
 	{
 		/*
-		 * See comments in FileRead()
+		 * See comments in FileReadV()
 		 */
 #ifdef WIN32
 		DWORD		error = GetLastError();
diff --git a/src/include/storage/fd.h b/src/include/storage/fd.h
@@ -15,7 +15,7 @@
 /*
  * calls:
  *
- *	File {Close, Read, Write, Size, Sync}
+ *	File {Close, Read, ReadV, Write, WriteV, Size, Sync}
  *	{Path Name Open, Allocate, Free} File
  *
  * These are NOT JUST RENAMINGS OF THE UNIX ROUTINES.
@@ -43,6 +43,8 @@
 #ifndef FD_H
 #define FD_H
 
+#include "port/pg_iovec.h"
+
 #include <dirent.h>
 #include <fcntl.h>
 
@@ -105,8 +107,8 @@ 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, off_t amount, uint32 wait_event_info);
-extern int	FileRead(File file, void *buffer, size_t amount, off_t offset, uint32 wait_event_info);
-extern int	FileWrite(File file, const void *buffer, size_t amount, off_t offset, uint32 wait_event_info);
+extern int	FileReadV(File file, const struct iovec *ioc, int iovcnt, off_t offset, uint32 wait_event_info);
+extern int	FileWriteV(File file, const struct iovec *ioc, int iovcnt, off_t offset, uint32 wait_event_info);
 extern int	FileSync(File file, uint32 wait_event_info);
 extern int	FileZero(File file, off_t offset, off_t amount, uint32 wait_event_info);
 extern int	FileFallocate(File file, off_t offset, off_t amount, uint32 wait_event_info);
@@ -189,4 +191,28 @@ extern int	durable_unlink(const char *fname, int elevel);
 extern void SyncDataDirectory(void);
 extern int	data_sync_elevel(int elevel);
 
+static inline int
+FileRead(File file, void *buffer, size_t amount, off_t offset,
+		 uint32 wait_event_info)
+{
+	struct iovec iov = {
+		.iov_base = buffer,
+		.iov_len = amount
+	};
+
+	return FileReadV(file, &iov, 1, offset, wait_event_info);
+}
+
+static inline int
+FileWrite(File file, const void *buffer, size_t amount, off_t offset,
+		  uint32 wait_event_info)
+{
+	struct iovec iov = {
+		.iov_base = unconstify(void *, buffer),
+		.iov_len = amount
+	};
+
+	return FileWriteV(file, &iov, 1, offset, wait_event_info);
+}
+
 #endif							/* FD_H */
