Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests]

[Christoph Hellwig <hch@lst.de>]

I still think adding code to every filesystem to optimize for a rather
stupid use case is not a good idea.  I dropped out a bit from the
thread in the middle, but what was the real use case for lots of
concurrent fsyncs on the same inode again?

And what is the amount of performance you need?  If we go back to the
direct submission of REQ_FLUSH request from the earlier flush+fua
setups that were faster or high end storage, would that be enough for
you?

Below is a patch brining the optimization back.

	WARNING: completely untested!


Index: linux-2.6/block/blk-flush.c
===================================================================
--- linux-2.6.orig/block/blk-flush.c	2010-10-12 10:08:43.777004514 -0400
+++ linux-2.6/block/blk-flush.c	2010-10-12 10:10:37.547016093 -0400
@@ -143,6 +143,17 @@ struct request *blk_do_flush(struct requ
 	unsigned skip = 0;
 
 	/*
+	 * Just issue pure flushes directly.
+	 */
+	if (!blk_rq_sectors(rq)) {
+		if (!do_preflush) {
+			__blk_end_request_all(rq, 0);
+			return NULL;
+		}
+		return rq;
+	}
+
+	/*
 	 * Special case.  If there's data but flush is not necessary,
 	 * the request can be issued directly.
 	 *