From owner-freebsd-hackers Thu Nov 9 9:51: 1 2000 Delivered-To: freebsd-hackers@freebsd.org Received: from dayspring.firedrake.org (dayspring.firedrake.org [195.82.105.251]) by hub.freebsd.org (Postfix) with ESMTP id 44D4A37B479 for ; Thu, 9 Nov 2000 09:50:57 -0800 (PST) Received: from float by dayspring.firedrake.org with local (Exim 3.12 #1 (Debian)) id 13tvqc-0005gu-00; Thu, 09 Nov 2000 17:50:50 +0000 Date: Thu, 9 Nov 2000 17:50:50 +0000 From: void To: Dag-Erling Smorgrav Cc: hackers@FreeBSD.ORG Subject: Re: "iowait" CPU state Message-ID: <20001109175050.C21468@firedrake.org> References: <20001107054413.A1983@firedrake.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5i In-Reply-To: ; from des@ofug.org on Tue, Nov 07, 2000 at 04:13:30PM +0100 Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Tue, Nov 07, 2000 at 04:13:30PM +0100, Dag-Erling Smorgrav wrote: > void writes: > > I've been using Solaris a lot lately, and I've noticed that in e.g. > > top's output, it has a distinct CPU state called "iowait", which seems > > to be a pretty good indicator of how I/O-bound a system is. Is there > > any reason that FreeBSD doesn't have such a state? > > It has several, depending on the type of I/O the process is waiting > for: biord (waiting for a read operation to complete), biowr (waiting > for a write operation to complete), select (waiting for descriptors to > become readable / writable), etc. Is there any reason top couldn't add these up and report a %iowait like Solaris'? -- Ben 220 go.ahead.make.my.day ESMTP Postfix To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message