From owner-freebsd-current Mon Sep 14 11:14:04 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id LAA16838 for freebsd-current-outgoing; Mon, 14 Sep 1998 11:14:04 -0700 (PDT) (envelope-from owner-freebsd-current@FreeBSD.ORG) Received: from smtp03.primenet.com (smtp03.primenet.com [206.165.6.133]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id LAA16222; Mon, 14 Sep 1998 11:12:06 -0700 (PDT) (envelope-from tlambert@usr05.primenet.com) Received: (from daemon@localhost) by smtp03.primenet.com (8.8.8/8.8.8) id LAA08606; Mon, 14 Sep 1998 11:11:48 -0700 (MST) Received: from usr05.primenet.com(206.165.6.205) via SMTP by smtp03.primenet.com, id smtpd008588; Mon Sep 14 11:11:44 1998 Received: (from tlambert@localhost) by usr05.primenet.com (8.8.5/8.8.5) id LAA18415; Mon, 14 Sep 1998 11:11:38 -0700 (MST) From: Terry Lambert Message-Id: <199809141811.LAA18415@usr05.primenet.com> Subject: Re: Download of FreeBSD 3.0-SNAP To: joelh@gnu.org Date: Mon, 14 Sep 1998 18:11:38 +0000 (GMT) Cc: tlambert@primenet.com, tom@uniserve.com, gpalmer@FreeBSD.ORG, irc@cooltime.simplenet.com, freebsd-current@FreeBSD.ORG In-Reply-To: <199809141738.MAA08622@detlev.UUCP> from "Joel Ray Holveck" at Sep 14, 98 12:38:54 pm X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-current@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG > I'm no disk expert, so please tell me: what is tagged command > queueing? Is it the ability to have multiple outstanding requests, > with the device reordering the requests for optimal efficiency, and > relying on a cookie in the header to differentiate between requests? Yes. Think of it as "how much concurrency does my disk support?". For a single-user, sincgle-program-at-a-time system, this is not much of a bottleneck; for a server under load, it's the *primary* bottleneck. Note that David points out that FreeBSD *does* do elevator sorting; it's still not optimal, however, since physical and logical cylinder boundaries are infrequently the same on modern hardware. I have to look before I say any more (since I thought the code was removed circa 2.2.1). David says it's called on all "dumb" drivers (wd, etc.); I'm not sure the "Ultra" DMA EIDE drivers are still in this category. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message