Move pg_pwritev_with_retry() to src/common/file_utils.c

This commit moves pg_pwritev_with_retry(), a convenience wrapper of
pg_writev() able to handle partial writes, to common/file_utils.c so
that the frontend code is able to use it.  A first use-case targetted
for this routine is pg_basebackup and pg_receivewal, for the
zero-padding of a newly-initialized WAL segment.  This is used currently
in the backend when the GUC wal_init_zero is enabled (default).

Author: Bharath Rupireddy
Reviewed-by: Nathan Bossart, Thomas Munro
Discussion: https://postgr.es/m/CALj2ACUq7nAb7=bJNbK3yYmp-SZhJcXFR_pLk8un6XgDzDF3OA@mail.gmail.com

1 files changed, 67 insertions, 0 deletions

diff --git a/src/common/file_utils.c b/src/common/file_utils.c
index df4d6d240c0..eac05a13ed5 100644
--- a/src/common/file_utils.c
+++ b/src/common/file_utils.c
@@ -28,6 +28,7 @@
 #ifdef FRONTEND
 #include "common/logging.h"
 #endif
+#include "port/pg_iovec.h"
 
 #ifdef FRONTEND
 
@@ -460,3 +461,69 @@ get_dirent_type(const char *path,
 
 	return result;
 }
+
+/*
+ * pg_pwritev_with_retry
+ *
+ * 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)
+		{
+			/* We don't expect the kernel to write more than requested. */
+			Assert(part == 0);
+			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;
+}