Re: om2.6 What's currently showable ?

Florian Delizy <[email protected]>
Newsgroups gmane.linux.cluster.openmosix.devel
Message-ID <[email protected]>
>> Well, yes what date would be usefull ? the potential completion time ? or the start date ?
>>     
>
> Maybe both?  That way people can tell when that estimate was last
> revised?
>   
OK let's do that, I add a column for start date, planned ending, and 
last re-evaluation date when I can (seems you are currently modifying it 
:D )

>
>   
>>> Matt
>>>
>>> On Mon, 2006-07-24 at 15:37 +0000, Florian Delizy  wrote:
>>>   
>>>       
>>>> Vincent Hanquez wrote:
>>>>     
>>>>         
>>>>> On Mon, Jul 24, 2006 at 03:49:21PM +0200, Florian Delizy wrote:
>>>>>   
>>>>>       
>>>>>           
>>>>>> Well actually, that's the case ... If I choose to use the 2.6
>>>>>>         
>>>>>>             
>>> kernel, 
>>>   
>>>       
>>>>>> [CUT]
>>>>>>         
>>>>>>             
>>>>> Mmap is very complex syscall and very wide:
>>>>> - Anonymous private mmap is working already very well (that is the
>>>>>       
>>>>>           
>>> simplest)
>>>   
>>>       
>>>>> - File private mmap use to work, with the rinode thingie. not sure
>>>>>       
>>>>>           
>>> that's
>>>   
>>>       
>>>>>   still the case now .. not tested for a while as well.
>>>>> - Anonymous shared mmap are not suppose to work yet, and should
>>>>>           
> send
>   
>>>>>   back the process to the deputy. untested.
>>>>> - File shared mmap are not suppose to work either. untested
>>>>>
>>>>> all shared mmaping can be made to work though. with some
>>>>> read only mapping to catch write fault, and have handler to
>>>>>       
>>>>>           
>>> propagate
>>>   
>>>       
>>>>> stuff.. the performance now is another thing ..
>>>>>
>>>>>   
>>>>>       
>>>>>           
>>>> ok, I added that to the todolist as well
>>>>
>>>> http://openmosix.snarc.org/wakka.php?wiki=ToDo
>>>>
>>>>     
>>>>         
>>>>>> This choice is quite important to me, and moreover, I can only
>>>>>>             
> help
>   
>>>>>>         
>>>>>>             
>>>   
>>>       
>>>>>> continuing to develop oM if I can proove the feasability with
>>>>>>             
> oM2.6
>   
>>>>>>     
>>>>>>         
>>>>>>             
>>>>> OM on 2.6 is definitely feasible. A experienced developer full
>>>>>           
> time
>   
>>>>>       
>>>>>           
>>> on
>>>   
>>>       
>>>>> it should complete it in few weeks I guess.
>>>>>
>>>>>   
>>>>>       
>>>>>           
>>>>>> I am not sure that would be enough ... though ... I guess that
>>>>>>         
>>>>>>             
>>> programs 
>>>   
>>>       
>>>>>> that we have to migrate are something like, using a shared lib,
>>>>>>             
> now
>   
>>>>>>         
>>>>>>             
>>> the 
>>>   
>>>       
>>>>>> question is how would taht be done ... (I don't know yet). A
>>>>>>             
> simple
>   
>>>>>>         
>>>>>>             
>>>   
>>>       
>>>>>> scenario, if several programs are using a single shared lib, and
>>>>>>         
>>>>>>             
>>> all 
>>>   
>>>       
>>>>>> programs are spread over different cluster nodes, would that work
>>>>>>             
> ?
>   
>>>>>>     
>>>>>>         
>>>>>>             
>>>>> yes it definitively works. a shared lib is anyway a private
>>>>>           
> mapping
>   
>>>>>       
>>>>>           
>>> (or
>>>   
>>>       
>>>>> a shared mapping over non-writable stuff, which is the same as
>>>>>       
>>>>>           
>>> private).
>>>   
>>>       
>>>>>   
>>>>>       
>>>>>           
>>>>     
>>>>         
> -------------------------------------------------------------------------
>   
>>>   
>>>       
>>>> Take Surveys. Earn Cash. Influence the Future of IT
>>>> Join SourceForge.net's Techsay panel and you'll get the chance to
>>>>     
>>>>         
>>> share your
>>>   
>>>       
>>>> opinions on IT & business topics through brief surveys -- and earn
>>>>     
>>>>         
>>> cash
>>>   
>>>
>>>       
> http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
>   
>>>   
>>>       
>>>> _______________________________________________
>>>> openMosix-devel mailing list
>>>> openMosix-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org
>>>> https://lists.sourceforge.net/lists/listinfo/openmosix-devel
>>>>     
>>>>         
>>>   
>>>       
>>
>>     
> -------------------------------------------------------------------------
>   
>> Take Surveys. Earn Cash. Influence the Future of IT
>> Join SourceForge.net's Techsay panel and you'll get the chance to
>>     
> share your
>   
>> opinions on IT & business topics through brief surveys -- and earn
>>     
> cash
>   
> http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
>   
>> _______________________________________________
>> openMosix-devel mailing list
>> openMosix-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org
>> https://lists.sourceforge.net/lists/listinfo/openmosix-devel
>>     
>
>
> -------------------------------------------------------------------------
> Take Surveys. Earn Cash. Influence the Future of IT
> Join SourceForge.net's Techsay panel and you'll get the chance to share your
> opinions on IT & business topics through brief surveys -- and earn cash
> http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
> _______________________________________________
> openMosix-devel mailing list
> openMosix-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org
> https://lists.sourceforge.net/lists/listinfo/openmosix-devel
>
>   


-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys -- and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.