Revise pg_pwrite_zeros()

The following changes are made to pg_write_zeros(), the API able to
write series of zeros using vectored I/O:
- Add of an "offset" parameter, to write the size from this position
(the 'p' of "pwrite" seems to mean position, though POSIX does not
outline ythat directly), hence the name of the routine is incorrect if
it is not able to handle offsets.
- Avoid memset() of "zbuffer" on every call.
- Avoid initialization of the whole IOV array if not needed.
- Group the trailing write() call with the main write() call,
simplifying the function logic.

Author: Andres Freund
Reviewed-by: Michael Paquier, Bharath Rupireddy
Discussion: https://postgr.es/m/[email protected]

4 files changed, 24 insertions, 44 deletions

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 87af608d15..543d4d897a 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -2982,7 +2982,7 @@ XLogFileInitInternal(XLogSegNo logsegno, TimeLineID logtli,
 		 * indirect blocks are down on disk.  Therefore, fdatasync(2) or
 		 * O_DSYNC will be sufficient to sync future writes to the log file.
 		 */
-		rc = pg_pwrite_zeros(fd, wal_segment_size);
+		rc = pg_pwrite_zeros(fd, wal_segment_size, 0);
 
 		if (rc < 0)
 			save_errno = errno;
diff --git a/src/bin/pg_basebackup/walmethods.c b/src/bin/pg_basebackup/walmethods.c
index 54014e2b84..6d14b988cb 100644
--- a/src/bin/pg_basebackup/walmethods.c
+++ b/src/bin/pg_basebackup/walmethods.c
@@ -222,7 +222,7 @@ dir_open_for_write(WalWriteMethod *wwmethod, const char *pathname,
 	{
 		ssize_t		rc;
 
-		rc = pg_pwrite_zeros(fd, pad_to_size);
+		rc = pg_pwrite_zeros(fd, pad_to_size, 0);
 
 		if (rc < 0)
 		{
diff --git a/src/common/file_utils.c b/src/common/file_utils.c
index 4dae534152..f19ebfa283 100644
--- a/src/common/file_utils.c
+++ b/src/common/file_utils.c
@@ -531,68 +531,48 @@ pg_pwritev_with_retry(int fd, const struct iovec *iov, int iovcnt, off_t offset)
 /*
  * pg_pwrite_zeros
  *
- * Writes zeros to file worth "size" bytes, using vectored I/O.
+ * Writes zeros to file worth "size" bytes at "offset" (from the start of the
+ * file), using vectored I/O.
  *
  * Returns the total amount of data written.  On failure, a negative value
  * is returned with errno set.
  */
 ssize_t
-pg_pwrite_zeros(int fd, size_t size)
+pg_pwrite_zeros(int fd, size_t size, off_t offset)
 {
-	PGAlignedBlock zbuffer;		/* worth BLCKSZ */
-	size_t		zbuffer_sz;
+	const static PGAlignedBlock zbuffer = {0};	/* worth BLCKSZ */
+	void	   *zerobuf_addr = unconstify(PGAlignedBlock *, &zbuffer)->data;
 	struct iovec iov[PG_IOV_MAX];
-	int			blocks;
-	size_t		remaining_size = 0;
-	int			i;
-	ssize_t		written;
+	size_t		remaining_size = size;
 	ssize_t		total_written = 0;
 
-	zbuffer_sz = sizeof(zbuffer.data);
-
-	/* Zero-fill the buffer. */
-	memset(zbuffer.data, 0, zbuffer_sz);
-
-	/* Prepare to write out a lot of copies of our zero buffer at once. */
-	for (i = 0; i < lengthof(iov); ++i)
-	{
-		iov[i].iov_base = zbuffer.data;
-		iov[i].iov_len = zbuffer_sz;
-	}
-
 	/* Loop, writing as many blocks as we can for each system call. */
-	blocks = size / zbuffer_sz;
-	remaining_size = size % zbuffer_sz;
-	for (i = 0; i < blocks;)
+	while (remaining_size > 0)
 	{
-		int			iovcnt = Min(blocks - i, lengthof(iov));
-		off_t		offset = i * zbuffer_sz;
-
-		written = pg_pwritev_with_retry(fd, iov, iovcnt, offset);
+		int			iovcnt = 0;
+		ssize_t		written;
 
-		if (written < 0)
-			return written;
-
-		i += iovcnt;
-		total_written += written;
-	}
+		for (; iovcnt < PG_IOV_MAX && remaining_size > 0; iovcnt++)
+		{
+			size_t		this_iov_size;
 
-	/* Now, write the remaining size, if any, of the file with zeros. */
-	if (remaining_size > 0)
-	{
-		/* We'll never write more than one block here */
-		int			iovcnt = 1;
+			iov[iovcnt].iov_base = zerobuf_addr;
 
-		/* Jump on to the end of previously written blocks */
-		off_t		offset = i * zbuffer_sz;
+			if (remaining_size < BLCKSZ)
+				this_iov_size = remaining_size;
+			else
+				this_iov_size = BLCKSZ;
 
-		iov[0].iov_len = remaining_size;
+			iov[iovcnt].iov_len = this_iov_size;
+			remaining_size -= this_iov_size;
+		}
 
 		written = pg_pwritev_with_retry(fd, iov, iovcnt, offset);
 
 		if (written < 0)
 			return written;
 
+		offset += written;
 		total_written += written;
 	}
 
diff --git a/src/include/common/file_utils.h b/src/include/common/file_utils.h
index bda6d3a541..b7efa1226d 100644
--- a/src/include/common/file_utils.h
+++ b/src/include/common/file_utils.h
@@ -44,6 +44,6 @@ extern ssize_t pg_pwritev_with_retry(int fd,
 									 int iovcnt,
 									 off_t offset);
 
-extern ssize_t pg_pwrite_zeros(int fd, size_t size);
+extern ssize_t pg_pwrite_zeros(int fd, size_t size, off_t offset);
 
 #endif							/* FILE_UTILS_H */