Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 17 Feb 2002 15:36:56 -0800 (PST)
From:      Matthew Dillon <dillon@apollo.backplane.com>
To:        Michael Smith <msmith@FreeBSD.ORG>
Cc:        Michael Smith <msmith@FreeBSD.ORG>, Poul-Henning Kamp <phk@critter.freebsd.dk>, Bruce Evans <bde@zeta.org.au>, freebsd-current@FreeBSD.ORG
Subject:   Re: ACPI timer is screwed... (was Re: 'microuptime() went backwards ...' using ACPI timer. Shouldn't that be impossible? ) 
Message-ID:  <200202172336.g1HNaup07553@apollo.backplane.com>
References:   <200202172327.g1HNRuA01838@mass.dis.org>

next in thread | previous in thread | raw e-mail | index | archive | help

:Sounds like we need to smack whoever made your chipset as well.  Intel 
:learned their lesson (finally) with later revisions of the PIIX4.  I'm 
:guessing you're running this against a ServerWorks system.

atapci0: <ServerWorks ROSB4 ATA33 controller> port 0x8b0-0x8bf at device 15.1 on
 pci0

    Uh huh.

    It might be possible to detect the situation during init-time by 
    explicitly looking for a reverse indexed time in a tight loop of 
    maybe a thousand reads, but that would still leave us with a statistical
    chance of not guessing right.

:Interesting.  This would be reasonably robust in the ripple-counter case 
:we have to deal with on the old PIIX4.  Have you tried implementing the 
:above yet, or measuring how much it costs?
:
:At any rate, please let me know for sure whether you're running on a 
:ServerWorks board, and I'll see if I can't find a Big Stick to hit them 
:with.
:
:Thanks,
:Mike

    I haven't measured the cost (extra loops) but I expect it would stabilize
    in no more then one additional loop, which would be three counter reads
    total or roughly the same as your originaln _safe code in the worst case.

    I think we could default to the _safe version and then explicitly change
    it to use the fast version if we see specific chipsets which we know
    to be good.

						-Matt



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




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200202172336.g1HNaup07553>