Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 21 Jul 2010 11:04:37 +0200
From:      Ivan Voras <ivoras@freebsd.org>
To:        Bruce Evans <brde@optusnet.com.au>
Cc:        svn-src-head@freebsd.org, svn-src-all@freebsd.org, src-committers@freebsd.org, John Baldwin <jhb@freebsd.org>
Subject:   Re: svn commit: r210217 - head/sys/kern
Message-ID:  <AANLkTilQm_nP-GAd-KHJPjdJcB8gX58dnI7f6xmpCpJp@mail.gmail.com>
In-Reply-To: <20100721134319.E7228@delplex.bde.org>
References:  <201007181015.o6IAFXvK018739@svn.freebsd.org> <201007190829.21995.jhb@freebsd.org>  <20100721134319.E7228@delplex.bde.org>

next in thread | previous in thread | raw e-mail | index | archive | help
On 21 July 2010 06:18, Bruce Evans <brde@optusnet.com.au> wrote:
> On Mon, 19 Jul 2010, John Baldwin wrote:
>
>>> Log:
>>> =C2=A0In keeping with the Age-of-the-fruitbat theme, scale up hirunning=
space
>>> on
>>> =C2=A0machines which can clearly afford the memory.
>>>
>>> =C2=A0This is a somewhat conservative version of the patch - more fine =
tuning
>>> may be
>>> =C2=A0necessary.
>>>
>>> =C2=A0Idea from: Thread on hackers@
>>> =C2=A0Discussed with: alc
>
> Sorry I didn't look at the thread, but I wonder if you should increase
> lorunningspace similarly.

The previous ratio of lorunningspace to hirunningspace was 1/2 - is
this still a good target?

> There is a possibly related problem with writing through file systems to
> high-latency disk devices like dvds. =C2=A0getblk() often takes many seco=
nds,
> and occasionally takes a couple of _minutes_. =C2=A0dvd's aren't quite th=
at
> slow, and can easily write hirunningspace =3D 1MB in 1 second, except
> possibly if the file system is not designed for high-latency devices
> (like most including cd9660 and udf are :-() so it does lots of random
> i/o).
>
> The above is mostly for 1 active file system...

It does seem like there would be more benefitial to hang these
variables per mount-point or something similar but I'm content that
they are tunable and that the new values help high-end machines,
probably in cooperation with tagged (NCQ-like) IO.

>> Presumably you could use 'lmax(lmin(..., 16 * 1024 * 1024), 1024 *
>> 1024))'?
>
> Better.

> Normal formatting is sometimes broken to avoid lines longer than 80
> characters. =C2=A0This works here. =C2=A0I don't like this.

Yes, this was the reason for the original patch's formatting :)



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?AANLkTilQm_nP-GAd-KHJPjdJcB8gX58dnI7f6xmpCpJp>