Re: broken VM in 2.4.10-pre9

[Christoph Hellwig <hch@ns.caldera.de>]

On Thu, Sep 20, 2001 at 12:16:56PM +0900, GOTO Masanori wrote:
> At Thu, 20 Sep 2001 00:26:05 +0200,
> Christoph Hellwig <hch@ns.caldera.de> wrote:
> > > "One argument for reverse mappings is distributed shared memory or
> > > distributed file systems and their interaction with memory mapped files.
> > > For example, a distributed file system may need to invalidate a specific
> > > page of a file that may be mapped multiple times on a node."
> > 
> > Please take a look at zap_inode_mappings in -ac.
> 
> zap_inode_mapping ?

Yes.

> 
> > Currently it only invalidates a whole mapping, but we can easily add
> > offset and lenght (and will probably do).
> 
> Adding offset/length support is good. 
> Did you mean that replacing zap_inode_mapping into more parts like
> zap_inode_mapping_whole and zap_inode_mapping_range ?

That depends.  For 2.4 at least we (the OpenGFS Project) probably won't
need it - and I didn't hear from other groups that need such functionality
yet.

	Christoph

-- 
Of course it doesn't work. We've performed a software upgrade.