Make WAL segment size configurable at initdb time.

For performance reasons a larger segment size than the default 16MB
can be useful. A larger segment size has two main benefits: Firstly,
in setups using archiving, it makes it easier to write scripts that
can keep up with higher amounts of WAL, secondly, the WAL has to be
written and synced to disk less frequently.

But at the same time large segment size are disadvantageous for
smaller databases. So far the segment size had to be configured at
compile time, often making it unrealistic to choose one fitting to a
particularly load. Therefore change it to a initdb time setting.

This includes a breaking changes to the xlogreader.h API, which now
requires the current segment size to be configured.  For that and
similar reasons a number of binaries had to be taught how to recognize
the current segment size.

Author: Beena Emerson, editorialized by Andres Freund
Reviewed-By: Andres Freund, David Steele, Kuntal Ghosh, Michael
    Paquier, Peter Eisentraut, Robert Hass, Tushar Ahuja
Discussion: https://postgr.es/m/CAOG9ApEAcQ--1ieKbhFzXSQPw_YLmepaa4hNdnY5+ZULpt81Mw@mail.gmail.com

1 files changed, 17 insertions, 15 deletions

diff --git a/src/backend/access/transam/xlogreader.c b/src/backend/access/transam/xlogreader.c
index 0781a7b9de9..b1f9b90c50f 100644
--- a/src/backend/access/transam/xlogreader.c
+++ b/src/backend/access/transam/xlogreader.c
@@ -64,7 +64,8 @@ report_invalid_record(XLogReaderState *state, const char *fmt,...)
  * Returns NULL if the xlogreader couldn't be allocated.
  */
 XLogReaderState *
-XLogReaderAllocate(XLogPageReadCB pagereadfunc, void *private_data)
+XLogReaderAllocate(int wal_segment_size, XLogPageReadCB pagereadfunc,
+				   void *private_data)
 {
 	XLogReaderState *state;
 
@@ -91,6 +92,7 @@ XLogReaderAllocate(XLogPageReadCB pagereadfunc, void *private_data)
 		return NULL;
 	}
 
+	state->wal_segment_size = wal_segment_size;
 	state->read_page = pagereadfunc;
 	/* system_identifier initialized to zeroes above */
 	state->private_data = private_data;
@@ -466,8 +468,8 @@ XLogReadRecord(XLogReaderState *state, XLogRecPtr RecPtr, char **errormsg)
 		(record->xl_info & ~XLR_INFO_MASK) == XLOG_SWITCH)
 	{
 		/* Pretend it extends to end of segment */
-		state->EndRecPtr += XLogSegSize - 1;
-		state->EndRecPtr -= state->EndRecPtr % XLogSegSize;
+		state->EndRecPtr += state->wal_segment_size - 1;
+		state->EndRecPtr -= XLogSegmentOffset(state->EndRecPtr, state->wal_segment_size);
 	}
 
 	if (DecodeXLogRecord(state, record, errormsg))
@@ -509,8 +511,8 @@ ReadPageInternal(XLogReaderState *state, XLogRecPtr pageptr, int reqLen)
 
 	Assert((pageptr % XLOG_BLCKSZ) == 0);
 
-	XLByteToSeg(pageptr, targetSegNo);
-	targetPageOff = (pageptr % XLogSegSize);
+	XLByteToSeg(pageptr, targetSegNo, state->wal_segment_size);
+	targetPageOff = XLogSegmentOffset(pageptr, state->wal_segment_size);
 
 	/* check whether we have all the requested data already */
 	if (targetSegNo == state->readSegNo && targetPageOff == state->readOff &&
@@ -719,16 +721,16 @@ ValidXLogPageHeader(XLogReaderState *state, XLogRecPtr recptr,
 
 	Assert((recptr % XLOG_BLCKSZ) == 0);
 
-	XLByteToSeg(recptr, segno);
-	offset = recptr % XLogSegSize;
+	XLByteToSeg(recptr, segno, state->wal_segment_size);
+	offset = XLogSegmentOffset(recptr, state->wal_segment_size);
 
-	XLogSegNoOffsetToRecPtr(segno, offset, recaddr);
+	XLogSegNoOffsetToRecPtr(segno, offset, recaddr, state->wal_segment_size);
 
 	if (hdr->xlp_magic != XLOG_PAGE_MAGIC)
 	{
 		char		fname[MAXFNAMELEN];
 
-		XLogFileName(fname, state->readPageTLI, segno);
+		XLogFileName(fname, state->readPageTLI, segno, state->wal_segment_size);
 
 		report_invalid_record(state,
 							  "invalid magic number %04X in log segment %s, offset %u",
@@ -742,7 +744,7 @@ ValidXLogPageHeader(XLogReaderState *state, XLogRecPtr recptr,
 	{
 		char		fname[MAXFNAMELEN];
 
-		XLogFileName(fname, state->readPageTLI, segno);
+		XLogFileName(fname, state->readPageTLI, segno, state->wal_segment_size);
 
 		report_invalid_record(state,
 							  "invalid info bits %04X in log segment %s, offset %u",
@@ -775,10 +777,10 @@ ValidXLogPageHeader(XLogReaderState *state, XLogRecPtr recptr,
 								  fhdrident_str, sysident_str);
 			return false;
 		}
-		else if (longhdr->xlp_seg_size != XLogSegSize)
+		else if (longhdr->xlp_seg_size != state->wal_segment_size)
 		{
 			report_invalid_record(state,
-								  "WAL file is from different database system: incorrect XLOG_SEG_SIZE in page header");
+								  "WAL file is from different database system: incorrect segment size in page header");
 			return false;
 		}
 		else if (longhdr->xlp_xlog_blcksz != XLOG_BLCKSZ)
@@ -792,7 +794,7 @@ ValidXLogPageHeader(XLogReaderState *state, XLogRecPtr recptr,
 	{
 		char		fname[MAXFNAMELEN];
 
-		XLogFileName(fname, state->readPageTLI, segno);
+		XLogFileName(fname, state->readPageTLI, segno, state->wal_segment_size);
 
 		/* hmm, first page of file doesn't have a long header? */
 		report_invalid_record(state,
@@ -807,7 +809,7 @@ ValidXLogPageHeader(XLogReaderState *state, XLogRecPtr recptr,
 	{
 		char		fname[MAXFNAMELEN];
 
-		XLogFileName(fname, state->readPageTLI, segno);
+		XLogFileName(fname, state->readPageTLI, segno, state->wal_segment_size);
 
 		report_invalid_record(state,
 							  "unexpected pageaddr %X/%X in log segment %s, offset %u",
@@ -832,7 +834,7 @@ ValidXLogPageHeader(XLogReaderState *state, XLogRecPtr recptr,
 		{
 			char		fname[MAXFNAMELEN];
 
-			XLogFileName(fname, state->readPageTLI, segno);
+			XLogFileName(fname, state->readPageTLI, segno, state->wal_segment_size);
 
 			report_invalid_record(state,
 								  "out-of-sequence timeline ID %u (after %u) in log segment %s, offset %u",