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

1 files changed, 3 insertions, 27 deletions

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 246869bba29..7eed5866d2e 100644
--- a/src/backend/access/transam/xlog.c
+++ b/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];