From owner-freebsd-hackers  Tue Dec 12 22:21:31 2000
From owner-freebsd-hackers@FreeBSD.ORG  Tue Dec 12 22:21:27 2000
Return-Path: <owner-freebsd-hackers@FreeBSD.ORG>
Delivered-To: freebsd-hackers@freebsd.org
Received: from earth.backplane.com (placeholder-dcat-1076843399.broadbandoffice.net [64.47.83.135])
	by hub.freebsd.org (Postfix) with ESMTP
	id 4004637B400; Tue, 12 Dec 2000 22:21:27 -0800 (PST)
Received: (from dillon@localhost)
	by earth.backplane.com (8.11.1/8.9.3) id eBD6LPa80568;
	Tue, 12 Dec 2000 22:21:25 -0800 (PST)
	(envelope-from dillon)
Date: Tue, 12 Dec 2000 22:21:25 -0800 (PST)
From: Matt Dillon <dillon@earth.backplane.com>
Message-Id: <200012130621.eBD6LPa80568@earth.backplane.com>
To: freebsd-stable@FreeBSD.ORG, freebsd-hackers@FreeBSD.ORG
Cc: Kachun Lee <kachun@pathlink.com>, Paul Saab <paul@mu.org>
Subject: Patches available (was Re: Extreme high load with 12/7 4-releng)
References: <200012120230.SAA32402@pathlink.net>
 <200012121801.KAA42878@pathlink.net> <200012122138.NAA69074@pathlink.net> <200012122231.eBCMVE353411@earth.backplane.com> <200012130209.eBD290M79194@earth.backplane.com>
Sender: owner-freebsd-hackers@FreeBSD.ORG
Precedence: bulk
X-Loop: FreeBSD.ORG

    I have made a patchset available for both -current and -stable on my site:

	http://apollo.backplane.com/FreeBSD4/

    This patchset contains debugging code for the pageout daemon which can be
    turned on with:

	sysctl -w vm.debug_pageout_stats=1

    The debugging code prints a line to dmesg and /var/log/messages each
    time the pageout daemon runs a scan, and tells you how many clean pages,
    dirty pages, and skipped pages were scanned, as well as the calculated
    page deficit for the invalid queue scan and the active queue scan.
    This output would be invaluable to me coming from people who still have
    major performance problems on heavily loaded machines.

    I would appreciate wide testing, especially by anyone running heavily
    loaded -stable boxes.  I am especially interested in how this patchset
    performs on news boxes.

    Pleae keep in mind that -current is unstable at the moment and that the
    instability has nothing to do with this or other VM/low-memory related
    patchsets.

    (Paul, I'm cc'ing you to see if you could run those heavy-load tests
    with this patchset.  My tests showed a remarkable improvement in response
    times).

						-Matt



To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message