From: Premoli, R. [ITPPG/1010] <rob...@ph...> - 2004-06-23 11:43:11
|
For better understand, I sen some questions (see below) >2.4.26 be oMFS-less, add the mighsm compile-time option, and >features-checker >In 2.4.26 we will also eliminate oMFS support. oMFS will, in time, be >replaced by integration with oGFS, Lustre, PVFS. it seams you worked a lot to do oMFS... why did you have idea to remove this feature? >For 2.6, we are (in summary): >Moving all code we can from kernel to user-space, but zero configuration >operation is still the goal, just as in 2.4. Do you want move up openMosix from kernel-space like to create a "layer" between kernel-space and user-space? If yes, why? I think if openMosix is inside the kernel, it is more efficent/responsive: isn't it? >Plus, there will be cleanups or a total rewrite of some parts. >openGFS is a long-term goal, but not immediate for 2.6. >Integration of InfiniBand drivers Can you better detail openGFS and Infiniband Drivers? Thanks, Roberto This communication is intended solely for the use of the addressee and may contain information that is legally privileged, confidential or exempt from disclosure. If you are not the intended recipient, please note that any dissemination, distribution, or copying of this communication is strictly prohibited. Anyone who receives this message in error should notify the sender immediately and delete it from his or her computer. |