This patch optimize io_submit_one to call aio_run_iocb() directly if
ctx->run_list is empty.  When the list is empty, the operation of
adding to the list, then call to __aio_run_iocbs() is unnecessary
because these operations are done in one atomic step. ctx->run_list
always has only one element in this case.  This optimization speeds
up industry standard db transaction processing benchmark by 0.2%.

Signed-off-by: Ken Chen <kenneth.w.chen@intel.com>


--- linux-2.6.11/fs/aio.c.orig	2005-04-25 08:42:17.000000000 -0700
+++ linux-2.6.11/fs/aio.c	2005-04-25 09:10:27.000000000 -0700
@@ -1513,10 +1513,14 @@ int fastcall io_submit_one(struct kioctx
 		goto out_put_req;
 
 	spin_lock_irq(&ctx->ctx_lock);
-	list_add_tail(&req->ki_run_list, &ctx->run_list);
-	/* drain the run list */
-	while (__aio_run_iocbs(ctx))
-		;
+	if (likely(list_empty(&ctx->run_list))) {
+		aio_run_iocb(req);
+	} else {
+		list_add_tail(&req->ki_run_list, &ctx->run_list);
+		/* drain the run list */
+		while (__aio_run_iocbs(ctx))
+			;
+	}
 	spin_unlock_irq(&ctx->ctx_lock);
 	aio_put_req(req);	/* drop extra ref to req */
 	return 0;