[prev in list] [next in list] [prev in thread] [next in thread] 

List:       lustre-devel
Subject:    RE: [Lustre-devel] cobd + tmpfs
From:       "Kelleher, Liam" <Liam.Kelleher () hp ! com>
Date:       2003-04-11 16:08:06
[Download RAW message or body]

Hi Peter,
	I have looked again at tmpfs and the changes made in the 2.5 kernel that support the \
"missing" functionality and these as they stand are dependant on quite a number of \
other changes in the 2.5 kernel. So at this stage I do not think that I can just \
bring these changes back to the 2.4 kernel.   I am trying to see if there is another \
solution but if you have any thoughts I'd appreciate them.

-Liam

-----Original Message-----
From: Peter Braam [mailto:braam@clusterfs.com]
Sent: 10 April 2003 16:53
To: Kelleher, Liam
Cc: lustre-devel@lists.sourceforge.net; Desormeaux, Dave
Subject: Re: [Lustre-devel] (no subject)



Hi Liam, 

I think it would be easiest to some changes to 2.4 unless you want to
be involved in maintaining a very fast moving target..

- Peter -

On Wed, Apr 09, 2003 at 05:28:50PM +0100, Kelleher, Liam wrote:
> Hi,
> 	I sent a mail previously querying whether LLP was targetted at the 2.5 kernel \
> (attached below) and got a response to say it was. The reason I asked was due to \
> tmpfs support and integration with the cobd.   Radhika asked me to reopen the \
> discussion to see if there are any thoughts on integrating tmpfs and the obdfilter \
> layer with the 2.4 kernel.  Thanks,
> -Liam
> 	
> 	
> 
> Hi,
> I was wondering what the plan version of the kernel was being targetted for LLP.
> The reason that I ask is that I was looking into using tmpfs as the backing store \
> for the cobd. In the 2.4 rev of the kernel there is missing functionality such as \
> prepare_write() readpage() and commit_write()  in the tmpfs implementation which \
> would be needed I believe if interfacing with the obfilter layer. 
> This functionality is present in the V2.5 kernel. 
> 
> If we are not moving to the V2.5 kernel in the relatively short term should I look \
> at what might be needed to be done to get this functionality in the 2.4 kernel? \
> From an initial inpection this looks like a relatively non trivial task.  
> Thanks,
> Liam
> 
> 
> 
> -------------------------------------------------------
> This SF.net email is sponsored by: Etnus, makers of TotalView, The debugger
> for complex code. Debugging C/C++ programs can leave you feeling lost and
> disoriented. TotalView can help you find your way. Available on major UNIX
> and Linux platforms. Try it free. www.etnus.com
> _______________________________________________
> Lustre-devel mailing list
> Lustre-devel@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/lustre-devel
- Peter -


-------------------------------------------------------
This SF.net email is sponsored by: Etnus, makers of TotalView, The debugger 
for complex code. Debugging C/C++ programs can leave you feeling lost and 
disoriented. TotalView can help you find your way. Available on major UNIX 
and Linux platforms. Try it free. www.etnus.com
_______________________________________________
Lustre-devel mailing list
Lustre-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/lustre-devel


[prev in list] [next in list] [prev in thread] [next in thread] 

Configure | About | News | Add a list | Sponsored by KoreLogic