Date: Fri, 25 May 2001 13:06:13 -0700 From: Doug Barton <DougB@DougBarton.net> To: Mike Silbersack <silby@silby.com> Cc: Ed Hudson <elh_fbsd@spnet.com>, hackers@FreeBSD.ORG Subject: Re: general speed differences between 4.1.1-RELEASE and 4.3-RELEASE Message-ID: <3B0EBB35.2468C293@DougBarton.net> References: <20010525120231.L58983-100000@achilles.silby.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Mike Silbersack wrote:
>
> On Thu, 24 May 2001, Doug Barton wrote:
>
> > The current mood (which I agree with) is to make softupdates the default
> > after installation. The problem with the combo of write caching and
> > softupdates is that if the power actually goes off the meta-data writes
> > that softupdates postpones and are further postponed by the write cache
> > will never happen, therefore leaving the file system in a potentially
> > unrecoverable state.
>
> That mood is nice in theory, but doesn't seem to fit practice. My boxes
> are on UPSes, and I have trouble remembering the last time the power went
> out.
If you are confident that write cacheing is safe for you, it's still there
for you to enable. I'm talking about the defaults, which we always try to
balance between speed and safety; but more on the side of safety.
> On the other hand, I can clearly remember the last panic
> on my -current box which required a manual fsck to repair (yesterday).
> And yes, write caching was disabled on the box at the time. It seems to
> me that we're assuming hardware write caching is some evil villan which
> will steal our data without any evidence. At the same time, we're putting
> blind trust in filesystems to always DTRT.
No one is making that assumption. It has been discussed at great length (I
believe on -current) and Kirk has agreed that the combo of softupdates +
write cacheing is very dangerous and should be avoided as a default. Users
like you with more advanced knowledge of how things work are free to do as
they see fit.
> And stuck in the middle is a growing number of people who are seeing a
> noticeable slowdown with 4.3, and will start telling their friends that
> FreeBSD is slow.
I would _much_ rather they say it's slow then say it ate their data.
--
I need someone really bad. Are you really bad?
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3B0EBB35.2468C293>