From owner-freebsd-hackers  Sat Mar  8 22:39:32 1997
Return-Path: <owner-hackers>
Received: (from root@localhost)
          by freefall.freebsd.org (8.8.5/8.8.5) id WAA01078
          for hackers-outgoing; Sat, 8 Mar 1997 22:39:32 -0800 (PST)
Received: from scanner.worldgate.com (scanner.worldgate.com [198.161.84.3])
          by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id WAA01073;
          Sat, 8 Mar 1997 22:39:27 -0800 (PST)
Received: from znep.com (uucp@localhost) by scanner.worldgate.com (8.8.5/8.7.3) with UUCP id XAA06335; Sat, 8 Mar 1997 23:39:24 -0700 (MST)
Received: from localhost (marcs@localhost) by alive.znep.com (8.7.5/8.7.3) with SMTP id XAA09130; Sat, 8 Mar 1997 23:39:06 -0700 (MST)
Date: Sat, 8 Mar 1997 23:39:06 -0700 (MST)
From: Marc Slemko <marcs@znep.com>
To: "matthew c. mead" <mmead@goof.com>
cc: isp@freebsd.org, hackers@freebsd.org
Subject: Re: freebsd as a news server?
In-Reply-To: <199703090616.BAA12521@goof.com>
Message-ID: <Pine.BSF.3.95.970308232002.6158Q-100000@alive.znep.com>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: owner-hackers@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

On Sun, 9 Mar 1997, matthew c. mead wrote:

> 	Hmm.  The above seems to suggest that the practice of
> mounting async when doing a make work wouldn't help, but I recall
> it making a pretty measurable difference.  What I meant in the

In a make world there are a lot more files being updated (eg. when it
cleans the object tree) than in a kernel make.

> question I asked was, considering that I'm running 2.1.6,
> mounting async probably doesn't make any difference.  Is that the
> case?  Or am I just not testing things that would make any
> difference?  Thanks for the reply!

As I said, making a kernel will not show any big difference; try creating
and removing a large number of files. 

say something like:

#!/usr/bin/perl
for ($i = 0; $i < 1000; $i++) {
        open(F, ">test.$i");
        close F;
}
for ($i = 0; $i < 1000; $i++) {
        unlink("test.$i");
}

This gives me 36.62 seconds sync and a drive that sounds like it
is trying to chew on a pengiun vs. 22.99 async and an almost silent
drive.

There would be a bigger difference if:
	- there were other processes competing for the disk; the extra
	  seeks that being mounted sync generates would hurt a lot more.
	- the filesystem wasn't as clean; this was done an an empty,
	  unused filesystem.

As I posted earlier, the feature is there in 2.1.6.  It affects
more things in 2.2 but still has a big impact in 2.1 (I did the
above test on a 2.1-stable box) for the right things.  News is one
of those things.