inode checkpoints

[Artem Bityuckiy]

> 
> 
> I agree that these changes will benefit NAND the most, but they are also
> valuable for all flashes.  
> 
> Say I have a 16 MiB file on my NOR flash.  When a stat or open is done,
> iget is called, which calls readinode, which then goes and reads all the
> nodes off of the flash to build up the inode information.  I've seen
> that take upwards of 2 seconds, just because of the number of data nodes
> that have to be read.
> 
> Now, same situation, but I have a checkpoint node out there.  I don't
> have to read _all_ the data nodes because the checkpoint gives me a
> snapshot of at least some of them, right?
> 
> Or maybe I am extending your idea a bit further than what you
> intended...
> 
> josh
> 
You are right in general. I would like to say that the NAND ICPs idea is 
*superset* for NOR ICP idea, not vice versa... (ICP=inode check point)

But I believe the NOR ICPs shouldn't be implemented together with NAND 
cips since NOR ICPs are much simpler. For example, the need bych simpler 
data structures, algorithms, etc. I dont think it is a good Idea to have 
hunderds of #ifdefs ...

-- 
Best regards, Artem B. Bityuckiy
Oktet Labs (St. Petersburg), Software Engineer.
+78124286709 (office) +79112449030 (mobile)
E-mail: dedekind at oktetlabs.ru, web: http://www.oktetlabs.ru