This is now tested and committed to HEAD.
Please try it out, and if there is no problems I'll commit it to
Squid-2.4 as well.
/Henrik
Henrik Nordstrom wrote:
>
> Adrian Chadd wrote:
> >
> > On Fri, Feb 09, 2001, Henrik Nordstrom wrote:
> > > I fully agree. So the question is if should we move that -1 to a
> > > cache_dir option instead of being one of the mandatory arguments to
> > > cache_dir?
> > >
> > > If so, we should do it before 2.4.STABLE1 is rolled, so we need to
> > > decide NOW.
> >
> > I'm all for it.
>
> Ok. I have now implemented a genric cache_dir options parser using the
> syntax
>
> cache_dir type path [fs-specific arguments] [options...]
>
> fs-specific arguments are the arguments that must always be specified.
> For ufs,aufs,diskd this is
> size L1 L2
>
> Global options:
> read-only
> max-size
>
> diskd options:
> Q1=n (defaults to 64 if not specified)
> Q2=n (defaults to 72 if not specified)
>
> Ideally I'd like to make L1 and L2 options as well, but this will break
> syntax compability with Squid-2.3 so I have not yet done it.
>
> The changes are currently residing in the SourceForge branch "fsopts",
> but I will commit it to HEAD as soon as testing has finished, and unless
> someone objects to the idea I'd merge the changes back to Squid-2.4.
>
> Note: This change will in by opiniton bring the 2.4-PRE changes over the
> threshold that requires yet another PRE release before STABLE1, but I
> think it is worth it if nothing else because the less number of confused
> users in the upgrade process..
>
> /Henrik
Received on Sat Feb 10 2001 - 09:50:54 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:13:29 MST