Date: Wed, 14 Oct 1998 15:54:56 -0700 (PDT) From: tlambert@usr04.primenet.com To: undisclosed-recipients:; Message-ID: <199810142254.PAA12517@hub.freebsd.org>
next in thread | raw e-mail | index | archive | help
> > >Bottom line is that by default FreeBSD w/SoftUpdates is more *unstable*
> > >now with CAM than it was w/out CAM for 99% of the users.
> >
> > Please don't add any more FUD to this thread than there is already.
> >
> > CAM has nothing to do with this issue. Neither the old SCSI code nor the
> > new CAM code has ever modified the caching behavior of the devices attached
> > on the bus.
>
> Previous email imply that it has the ability to disable/enable
> write-caching the addition of quirks entries for certain devices.
Actually, the write-caching discussion is orthogonal, and has to do
with a seperate series on:
o How to enable write caching
o Write caching is bad
o No it's not
o Yes it is
o No it's not
o Yes it is, and here's an example of where it breaks things
o Machines don't reset except when they lose power
o Yes they do
o No they don't, and write caching isn't bad, it's the bogus
assumptions by soft updates that are bad
o No it isn't
o Yes it is
o No it isn't, because a sync mounted filesystem makes the
same assumptions about queue-order completion
Ok, ok, I've gone a little farther down the thread than the thread
has currently done, but it's really what's coming.
Terry Lambert
terry@lambert.org
From: Terry Lambert <tlambert@primenet.com>
Message-Id: <199810142251.PAA02490@usr04.primenet.com>
Subject: Re: filesystem safety and SCSI disk write caching
To: nate@mt.sri.com (Nate Williams)
Date: Wed, 14 Oct 1998 22:51:30 +0000 (GMT)
Cc: freebsd-scsi@FreeBSD.ORG
In-Reply-To: <199810141518.JAA05051@mt.sri.com> from "Nate Williams" at Oct 14,
98 09:18:56 am
X-Mailer: ELM [version 2.4 PL25]
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
> > >Bottom line is that by default FreeBSD w/SoftUpdates is more *unstable*
> > >now with CAM than it was w/out CAM for 99% of the users.
> >
> > Please don't add any more FUD to this thread than there is already.
> >
> > CAM has nothing to do with this issue. Neither the old SCSI code nor the
> > new CAM code has ever modified the caching behavior of the devices attached
> > on the bus.
>
> Previous email imply that it has the ability to disable/enable
> write-caching the addition of quirks entries for certain devices.
Actually, the write-caching discussion is orthogonal, and has to do
with a seperate series on:
o How to enable write caching
o Write caching is bad
o No it's not
o Yes it is
o No it's not
o Yes it is, and here's an example of where it breaks things
o Machines don't reset except when they lose power
o Yes they do
o No they don't, and write caching isn't bad, it's the bogus
assumptions by soft updates that are bad
o No it isn't
o Yes it is
o No it isn't, because a sync mounted filesystem makes the
same assumptions about queue-order completion
Ok, ok, I've gone a little farther down the thread than the thread
has currently done, but it's really what's coming.
Terry Lambert
terry@lambert.org
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-scsi" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199810142254.PAA12517>