Re: PATCH: Cygwin: file mode support and ufs writecleanswap bugfix

----- Original Message -----
From: "Duane Wessels" <wessels@squid-cache.org>
To: "Robert Collins" <robert.collins@itdomain.com.au>
Cc: <squid-dev@squid-cache.org>
Sent: Friday, January 05, 2001 1:09 PM
Subject: Re: PATCH: Cygwin: file mode support and ufs writecleanswap bugfix

>
>
> On Fri, 5 Jan 2001, Robert Collins wrote:
>
> > Sure I hate that too :]. What I meant was - the stats page doesn't
> > call a storefsDirGetBlkSize() which then calls the code you've
> > written if appropriate. The stats page calls it directly, so it
> > _will_ require new fs drivers to be statsfs-able.
>
> Sorry, I don't follow you.
>
> storeDirStats() doesn't call storeDirGetBlkSize().
>
> storeDirStats() prints the value of SD->fs.kperblk. This variable
> is initialized to 1 (i.e. 1KB/block) by default, which is what the
> old, hard-coded way assumed.
>
> You could argue that storeDirStats should not print fs.kperblk
> because some storage systems won't have a notion of block size.

Yup that's what I'm arguing.

>
> new fs drivers don't have to be statfs-able. They can leave the
> values at their defaults, which may or may not be meaningful. We
> can always change this in the future if we need to.
>
> Probably the right thing to do is make a FS method function
> that returns the actual space used, including overheads.
> I was too lazy to do it that way.
>
>

Yes I agree - the struct fs should probably be FS methods. And yes, I had the call path wrong.

Rob
Received on Thu Jan 04 2001 - 19:24:45 MST