[PATCH] LogFS take three

[Jamie Lokier]

Artem Bityutskiy wrote:
> On Wed, 2007-05-16 at 12:34 +0100, Jamie Lokier wrote:
> > Jörn Engel wrote:
> > > On Wed, 16 May 2007 12:54:14 +0800, David Woodhouse wrote:
> > > > Personally I'd just go for 'JFFS3'. After all, it has a better claim to
> > > > the name than either of its predecessors :)
> > > 
> > > Did you ever see akpm's facial expression when he tried to pronounce
> > > "JFFS2"?  ;)
> > 
> > JFFS3 is a good, meaningful name to anyone familiar with JFFS2.
> > 
> > But if akpm can't pronounce it, how about FFFS for faster flash
> > filesystem.... ;-)
> 
> The problem is that JFFS2 will always be faster in terms of I/O speed
> anyway, just because it does not have to maintain on-flash indexing
> data structures. But yes, it is slow in mount and in building big
> inodes, so the "faster" is confusing.

Is LogFS really slower than JFFS2 in practice?

I would have guessed reads to be a similar speed, tree updates to be a
similar speed  to journal  updates for sustained  non-fsyncing writes,
and the difference unimportant for tiny individual commits whose index
updates are not merged with any other.  I've not thought about it much
though.

-- Jamie