1 files changed, 108 insertions, 0 deletions
diff --git a/src/backend/storage/smgr/md.c b/src/backend/storage/smgr/md.c
index 352958e1feb..1c2d1405f86 100644
--- a/src/backend/storage/smgr/md.c
+++ b/src/backend/storage/smgr/md.c
@@ -501,6 +501,114 @@ mdextend(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 }
 
 /*
+ *	mdzeroextend() -- Add new zeroed out blocks to the specified relation.
+ *
+ *		Similar to mdextend(), except the relation can be extended by multiple
+ *		blocks at once and the added blocks will be filled with zeroes.
+ */
+void
+mdzeroextend(SMgrRelation reln, ForkNumber forknum,
+			 BlockNumber blocknum, int nblocks, bool skipFsync)
+{
+	MdfdVec    *v;
+	BlockNumber curblocknum = blocknum;
+	int			remblocks = nblocks;
+
+	Assert(nblocks > 0);
+
+	/* This assert is too expensive to have on normally ... */
+#ifdef CHECK_WRITE_VS_EXTEND
+	Assert(blocknum >= mdnblocks(reln, forknum));
+#endif
+
+	/*
+	 * If a relation manages to grow to 2^32-1 blocks, refuse to extend it any
+	 * more --- we mustn't create a block whose number actually is
+	 * InvalidBlockNumber or larger.
+	 */
+	if ((uint64) blocknum + nblocks >= (uint64) InvalidBlockNumber)
+		ereport(ERROR,
+				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
+				 errmsg("cannot extend file \"%s\" beyond %u blocks",
+						relpath(reln->smgr_rlocator, forknum),
+						InvalidBlockNumber)));
+
+	while (remblocks > 0)
+	{
+		BlockNumber	segstartblock = curblocknum % ((BlockNumber) RELSEG_SIZE);
+		off_t		seekpos = (off_t) BLCKSZ * segstartblock;
+		int			numblocks;
+
+		if (segstartblock + remblocks > RELSEG_SIZE)
+			numblocks = RELSEG_SIZE - segstartblock;
+		else
+			numblocks = remblocks;
+
+		v = _mdfd_getseg(reln, forknum, curblocknum, skipFsync, EXTENSION_CREATE);
+
+		Assert(segstartblock < RELSEG_SIZE);
+		Assert(segstartblock + numblocks <= RELSEG_SIZE);
+
+		/*
+		 * If available and useful, use posix_fallocate() (via FileAllocate())
+		 * to extend the relation. That's often more efficient than using
+		 * write(), as it commonly won't cause the kernel to allocate page
+		 * cache space for the extended pages.
+		 *
+		 * However, we don't use FileAllocate() for small extensions, as it
+		 * defeats delayed allocation on some filesystems. Not clear where
+		 * that decision should be made though? For now just use a cutoff of
+		 * 8, anything between 4 and 8 worked OK in some local testing.
+		 */
+		if (numblocks > 8)
+		{
+			int			ret;
+
+			ret = FileFallocate(v->mdfd_vfd,
+								seekpos, (off_t) BLCKSZ * numblocks,
+								WAIT_EVENT_DATA_FILE_EXTEND);
+			if (ret != 0)
+			{
+				ereport(ERROR,
+						errcode_for_file_access(),
+						errmsg("could not extend file \"%s\" with FileFallocate(): %m",
+							   FilePathName(v->mdfd_vfd)),
+						errhint("Check free disk space."));
+			}
+		}
+		else
+		{
+			int			ret;
+
+			/*
+			 * Even if we don't want to use fallocate, we can still extend a
+			 * bit more efficiently than writing each 8kB block individually.
+			 * pg_pwrite_zeroes() (via FileZero()) uses
+			 * pg_pwritev_with_retry() to avoid multiple writes or needing a
+			 * zeroed buffer for the whole length of the extension.
+			 */
+			ret = FileZero(v->mdfd_vfd,
+						   seekpos, (off_t) BLCKSZ * numblocks,
+						   WAIT_EVENT_DATA_FILE_EXTEND);
+			if (ret < 0)
+				ereport(ERROR,
+						errcode_for_file_access(),
+						errmsg("could not extend file \"%s\": %m",
+							   FilePathName(v->mdfd_vfd)),
+						errhint("Check free disk space."));
+		}
+
+		if (!skipFsync && !SmgrIsTemp(reln))
+			register_dirty_segment(reln, forknum, v);
+
+		Assert(_mdnblocks(reln, forknum, v) <= ((BlockNumber) RELSEG_SIZE));
+
+		remblocks -= numblocks;
+		curblocknum += numblocks;
+	}
+}
+
+/*
  *	mdopenfork() -- Open one fork of the specified relation.
  *
  * Note we only open the first segment, when there are multiple segments.