[linux-elitists] A modest proposal: SSD disk acceleration in kernel.

Ruben Safir ruben@mrbrklyn.com
Sat Oct 25 17:29:15 PDT 2008


Jim Thompson wrote:
> Greg KH wrote:
>   
>> On Fri, Oct 24, 2008 at 10:04:01PM +0200, Eugen Leitl wrote:
>>   
>>     
>>>> There's going to be some pretty radical changes in the next 5 years with
>>>> regards to how memory and "flash" start getting intermixed.  Don't worry
>>>>       
>>>>         
>>> Will we get GC on persistent objects, and no more filesystems? And
>>> just how well is Linux is going to play with that, I wonder.
>>>     
>>>       
>> If an object is "persistent", why would it ever be garbage collected?
>> :)
>>   
>>     
> because you deleted parts of it.
>   
>> Seriously, what are you talking about here, some type of object-based
>> filesystem? 
>>     
> Nope.. its an object store.
>   
>> That stuff was debunked long ago.  If you really want
>> something like that, just use a database on a raw partition/disk, and
>> you can have it today.  To try to do that in a "native" filesystem is
>> just foolish.
>>   
>>     
> Wait, why did you need to run your database on a *raw* partition 
> again?   Oh yeah, because its really an object store?
>   


I don't know what your talking about,  The file system is a database, 
and I'd rather be dead than have a file system
that doesn't have a hierarchical abstraction layer.

For ten years now I have heard the insanity that LISP will be everything 
and everything is becoming LISP.

Oh ... No..

I'm glad you like LISP.  I hate it, and I've gotten to the point of 
liking the LISP community even less.

that might be something to think about if you unwrap it from a bunch of 
parenthesis...

Ruben

>> Objects, sheesh, what decade is this anyway...
>>   
>>     
> Thus Sprach the Perl Generation.
>
> _______________________________________________
> linux-elitists mailing list
> linux-elitists@zgp.org
> http://allium.zgp.org/cgi-bin/mailman/listinfo/linux-elitists
>
>   



More information about the linux-elitists mailing list