Provide pg_preadv() and pg_pwritev().

Provide synchronous vectored file I/O routines.  These map to preadv()
and pwritev(), with fallback implementations for systems that don't have
them.  Also provide a wrapper pg_pwritev_with_retry() that automatically
retries on short writes.

Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us>
Reviewed-by: Andres Freund <andres@anarazel.de>
Discussion: https://postgr.es/m/CA%2BhUKGJA%2Bu-220VONeoREBXJ9P3S94Y7J%2BkqCnTYmahvZJwM%3Dg%40mail.gmail.com

1 files changed, 105 insertions, 2 deletions

diff --git a/src/port/pwrite.c b/src/port/pwrite.c
index 282b27115e5..e029f44bc0c 100644
--- a/src/port/pwrite.c
+++ b/src/port/pwrite.c
@@ -1,7 +1,7 @@
 /*-------------------------------------------------------------------------
  *
  * pwrite.c
- *	  Implementation of pwrite(2) for platforms that lack one.
+ *	  Implementation of pwrite[v](2) for platforms that lack one.
  *
  * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group
  *
@@ -9,7 +9,8 @@
  *	  src/port/pwrite.c
  *
  * Note that this implementation changes the current file position, unlike
- * the POSIX function, so we use the name pg_pwrite().
+ * the POSIX function, so we use the name pg_pwrite().  Likewise for the
+ * iovec version.
  *
  *-------------------------------------------------------------------------
  */
@@ -23,6 +24,9 @@
 #include <unistd.h>
 #endif
 
+#include "port/pg_iovec.h"
+
+#ifndef HAVE_PWRITE
 ssize_t
 pg_pwrite(int fd, const void *buf, size_t size, off_t offset)
 {
@@ -53,3 +57,102 @@ pg_pwrite(int fd, const void *buf, size_t size, off_t offset)
 	return write(fd, buf, size);
 #endif
 }
+#endif
+
+#ifndef HAVE_PWRITEV
+ssize_t
+pg_pwritev(int fd, const struct iovec *iov, int iovcnt, off_t offset)
+{
+#ifdef HAVE_WRITEV
+	if (iovcnt == 1)
+		return pg_pwrite(fd, iov[0].iov_base, iov[0].iov_len, offset);
+	if (lseek(fd, offset, SEEK_SET) < 0)
+		return -1;
+	return writev(fd, iov, iovcnt);
+#else
+	ssize_t 	sum = 0;
+	ssize_t 	part;
+
+	for (int i = 0; i < iovcnt; ++i)
+	{
+		part = pg_pwrite(fd, iov[i].iov_base, iov[i].iov_len, offset);
+		if (part < 0)
+		{
+			if (i == 0)
+				return -1;
+			else
+				return sum;
+		}
+		sum += part;
+		offset += part;
+		if (part < iov[i].iov_len)
+			return sum;
+	}
+	return sum;
+#endif
+}
+#endif
+
+/*
+ * A convenience wrapper for pg_pwritev() that retries on partial write.  If an
+ * error is returned, it is unspecified how much has been written.
+ */
+ssize_t
+pg_pwritev_with_retry(int fd, const struct iovec *iov, int iovcnt, off_t offset)
+{
+	struct iovec iov_copy[PG_IOV_MAX];
+	ssize_t		sum = 0;
+	ssize_t		part;
+
+	/* We'd better have space to make a copy, in case we need to retry. */
+	if (iovcnt > PG_IOV_MAX)
+	{
+		errno = EINVAL;
+		return -1;
+	}
+
+	for (;;)
+	{
+		/* Write as much as we can. */
+		part = pg_pwritev(fd, iov, iovcnt, offset);
+		if (part < 0)
+			return -1;
+
+#ifdef SIMULATE_SHORT_WRITE
+		part = Min(part, 4096);
+#endif
+
+		/* Count our progress. */
+		sum += part;
+		offset += part;
+
+		/* Step over iovecs that are done. */
+		while (iovcnt > 0 && iov->iov_len <= part)
+		{
+			part -= iov->iov_len;
+			++iov;
+			--iovcnt;
+		}
+
+		/* Are they all done? */
+		if (iovcnt == 0)
+		{
+			if (part > 0)
+				elog(ERROR, "unexpectedly wrote more than requested");
+			break;
+		}
+
+		/*
+		 * Move whatever's left to the front of our mutable copy and adjust the
+		 * leading iovec.
+		 */
+		Assert(iovcnt > 0);
+		memmove(iov_copy, iov, sizeof(*iov) * iovcnt);
+		Assert(iov->iov_len > part);
+		iov_copy[0].iov_base = (char *) iov_copy[0].iov_base + part;
+		iov_copy[0].iov_len -= part;
+		iov = iov_copy;
+	}
+
+	return sum;
+}